Pablo Oliva
@depo77.bsky.social
AI Engineer, curious and conscious.
Alleviate Your Exhaustion and Improve Your Focus When Running Agents
Running several agent sessions wears you down, and tired is when you stop reading what the agent hands back. That cost me a project. What helped was removing small frictions, not trying harder.
Running several agent sessions wears you down, and tired is when you stop reading what the agent hands back. That cost me a project. What helped was removing small frictions, not trying harder.
Alleviate Your Exhaustion and Improve Your Focus When Running Agents
Running several agent sessions wears you down, and tired is when you stop reading what the agent hands back. That cost me a project. What helped was removing small frictions, not trying harder.
pablooliva.de
September 6, 2026 at 1:54 PM
Alleviate Your Exhaustion and Improve Your Focus When Running Agents
Running several agent sessions wears you down, and tired is when you stop reading what the agent hands back. That cost me a project. What helped was removing small frictions, not trying harder.
Running several agent sessions wears you down, and tired is when you stop reading what the agent hands back. That cost me a project. What helped was removing small frictions, not trying harder.
AI Vendors Don’t Lock You In. They Lock You Out.
Every vendor evaluation I've sat through was built to spot lock-in. None was built to spot the reverse: an AI system that leaves with the record of how your company works.
Every vendor evaluation I've sat through was built to spot lock-in. None was built to spot the reverse: an AI system that leaves with the record of how your company works.
AI Vendors Don’t Lock You In. They Lock You Out.
Every vendor evaluation I've sat through was built to spot lock-in. None was built to spot the reverse: an AI system that leaves with the record of how your company works.
pablooliva.de
September 5, 2026 at 12:09 PM
AI Vendors Don’t Lock You In. They Lock You Out.
Every vendor evaluation I've sat through was built to spot lock-in. None was built to spot the reverse: an AI system that leaves with the record of how your company works.
Every vendor evaluation I've sat through was built to spot lock-in. None was built to spot the reverse: an AI system that leaves with the record of how your company works.
A Notes Plugin for People Redlining Their Agent Sessions
Agents finish a task and hand you three more problems at the exact moment you are trying to merge. I researched every way to annotate an agent session, found bb, and built the plugin myself in twenty minutes.
Agents finish a task and hand you three more problems at the exact moment you are trying to merge. I researched every way to annotate an agent session, found bb, and built the plugin myself in twenty minutes.
A Notes Plugin for People Redlining Their Agent Sessions
Agents finish a task and hand you three more problems at the exact moment you are trying to merge. I researched every way to annotate an agent session, found bb, and built the plugin myself in twenty minutes.
pablooliva.de
August 25, 2026 at 12:12 PM
A Notes Plugin for People Redlining Their Agent Sessions
Agents finish a task and hand you three more problems at the exact moment you are trying to merge. I researched every way to annotate an agent session, found bb, and built the plugin myself in twenty minutes.
Agents finish a task and hand you three more problems at the exact moment you are trying to merge. I researched every way to annotate an agent session, found bb, and built the plugin myself in twenty minutes.
N Newsletters to 1 Digest, Built for AI Engineers
I built a pipeline to do my AI-news reading for me. It summarizes, de-dupes across sources, throws out the noise, and hands back the twenty or thirty things that mattered. It's public now.
I built a pipeline to do my AI-news reading for me. It summarizes, de-dupes across sources, throws out the noise, and hands back the twenty or thirty things that mattered. It's public now.
N Newsletters to 1 Digest, Built for AI Engineers
I built a pipeline to do my AI-news reading for me. It summarizes, de-dupes across sources, throws out the noise, and hands back the twenty or thirty things that mattered. It's public now.
pablooliva.de
July 29, 2026 at 2:18 PM
N Newsletters to 1 Digest, Built for AI Engineers
I built a pipeline to do my AI-news reading for me. It summarizes, de-dupes across sources, throws out the noise, and hands back the twenty or thirty things that mattered. It's public now.
I built a pipeline to do my AI-news reading for me. It summarizes, de-dupes across sources, throws out the noise, and hands back the twenty or thirty things that mattered. It's public now.
I Sat on an Idea for 7 Years. AI Helped Me File for a Patent in 2 Weeks.
Seven years ago I had an idea, 3D-printed one part of it, and then got stuck for good. Here's why I finally handed it to AI, and the honest question I wanted answered.
Seven years ago I had an idea, 3D-printed one part of it, and then got stuck for good. Here's why I finally handed it to AI, and the honest question I wanted answered.
I Sat on an Idea for 7 Years. AI Helped Me File for a Patent in 2 Weeks.
Seven years ago I had an idea, 3D-printed one part of it, and then got stuck for good. Here's why I finally handed it to AI, and the honest question I wanted answered.
pablooliva.de
July 27, 2026 at 10:33 AM
I Sat on an Idea for 7 Years. AI Helped Me File for a Patent in 2 Weeks.
Seven years ago I had an idea, 3D-printed one part of it, and then got stuck for good. Here's why I finally handed it to AI, and the honest question I wanted answered.
Seven years ago I had an idea, 3D-printed one part of it, and then got stuck for good. Here's why I finally handed it to AI, and the honest question I wanted answered.
Securing an Always-On AI Agent at Home: A Journey Through Dead Ends
The honest record of securing an always-on AI agent with shell access at home: why firewalling it in place failed, how network segmentation and an ngrok tunnel worked instead, and a frank list of what it still doesn't protect…
The honest record of securing an always-on AI agent with shell access at home: why firewalling it in place failed, how network segmentation and an ngrok tunnel worked instead, and a frank list of what it still doesn't protect…
Securing an Always-On AI Agent at Home: A Journey Through Dead Ends
The honest record of securing an always-on AI agent with shell access at home: why firewalling it in place failed, how network segmentation and an ngrok tunnel worked instead, and a frank list of what it still doesn't protect against.
pablooliva.de
July 14, 2026 at 10:27 AM
Securing an Always-On AI Agent at Home: A Journey Through Dead Ends
The honest record of securing an always-on AI agent with shell access at home: why firewalling it in place failed, how network segmentation and an ngrok tunnel worked instead, and a frank list of what it still doesn't protect…
The honest record of securing an always-on AI agent with shell access at home: why firewalling it in place failed, how network segmentation and an ngrok tunnel worked instead, and a frank list of what it still doesn't protect…
Our AI Rollout Started With People, Not Processes
AI adoption runs on two tracks — top-down process automation and individual everyday work. We started with people: one shared, self-hosted AI tool for a sub-500-person company across several EU countries (LibreChat on Azure OpenAI in an EU region,…
AI adoption runs on two tracks — top-down process automation and individual everyday work. We started with people: one shared, self-hosted AI tool for a sub-500-person company across several EU countries (LibreChat on Azure OpenAI in an EU region,…
Our AI Rollout Started With People, Not Processes
AI adoption runs on two tracks — top-down process automation and individual everyday work. We started with people: one shared, self-hosted AI tool for a sub-500-person company across several EU countries (LibreChat on Azure OpenAI in an EU region, with Redakt PII detection in the stream). Here's why we sequenced it that way, and what's in the setup.
pablooliva.de
June 22, 2026 at 11:28 AM
Our AI Rollout Started With People, Not Processes
AI adoption runs on two tracks — top-down process automation and individual everyday work. We started with people: one shared, self-hosted AI tool for a sub-500-person company across several EU countries (LibreChat on Azure OpenAI in an EU region,…
AI adoption runs on two tracks — top-down process automation and individual everyday work. We started with people: one shared, self-hosted AI tool for a sub-500-person company across several EU countries (LibreChat on Azure OpenAI in an EU region,…
Give Your Coding Agent More Autonomy
I run a development pipeline with permissions off, then trace every session into LangSmith. The plain case for why: an objective record of what the agent did unattended, evals that catch model regressions before they cost me, and a loop where the agent reviews…
I run a development pipeline with permissions off, then trace every session into LangSmith. The plain case for why: an objective record of what the agent did unattended, evals that catch model regressions before they cost me, and a loop where the agent reviews…
Give Your Coding Agent More Autonomy
I run a development pipeline with permissions off, then trace every session into LangSmith. The plain case for why: an objective record of what the agent did unattended, evals that catch model regressions before they cost me, and a loop where the agent reviews its own behavior and patches my setup.
pablooliva.de
June 17, 2026 at 10:27 AM
Give Your Coding Agent More Autonomy
I run a development pipeline with permissions off, then trace every session into LangSmith. The plain case for why: an objective record of what the agent did unattended, evals that catch model regressions before they cost me, and a loop where the agent reviews…
I run a development pipeline with permissions off, then trace every session into LangSmith. The plain case for why: an objective record of what the agent did unattended, evals that catch model regressions before they cost me, and a loop where the agent reviews…
Which AI Should You Actually Use? I Built an AI for That.
Most people use a fraction of what AI tools can do. Sherpa is an open-source agent that interviews someone about their job and recommends which AI features actually fit their work.
Most people use a fraction of what AI tools can do. Sherpa is an open-source agent that interviews someone about their job and recommends which AI features actually fit their work.
Which AI Should You Actually Use? I Built an AI for That.
Most people use a fraction of what AI tools can do. Sherpa is an open-source agent that interviews someone about their job and recommends which AI features actually fit their work.
pablooliva.de
June 6, 2026 at 10:10 AM
Which AI Should You Actually Use? I Built an AI for That.
Most people use a fraction of what AI tools can do. Sherpa is an open-source agent that interviews someone about their job and recommends which AI features actually fit their work.
Most people use a fraction of what AI tools can do. Sherpa is an open-source agent that interviews someone about their job and recommends which AI features actually fit their work.
Claude Made an 18-Minute Tutorial of My App
I pointed Claude Code at our live internal product and had it film and narrate an 18-minute tutorial. The pipeline, the parts still done by hand, and how to reproduce it.
I pointed Claude Code at our live internal product and had it film and narrate an 18-minute tutorial. The pipeline, the parts still done by hand, and how to reproduce it.
Claude Made an 18-Minute Tutorial of My App
I pointed Claude Code at our live internal product and had it film and narrate an 18-minute tutorial. The pipeline, the parts still done by hand, and how to reproduce it.
pablooliva.de
June 1, 2026 at 4:18 PM
Claude Made an 18-Minute Tutorial of My App
I pointed Claude Code at our live internal product and had it film and narrate an 18-minute tutorial. The pipeline, the parts still done by hand, and how to reproduce it.
I pointed Claude Code at our live internal product and had it film and narrate an 18-minute tutorial. The pipeline, the parts still done by hand, and how to reproduce it.
Opus 4.7 is Terse
Opus 4.7's terser default style breaks down on complex projects. The fix is a custom output style that restores thorough explanations, plus evals to catch this kind of drift on future model releases.
Opus 4.7's terser default style breaks down on complex projects. The fix is a custom output style that restores thorough explanations, plus evals to catch this kind of drift on future model releases.
Opus 4.7 is Terse
Opus 4.7's terser default style breaks down on complex projects. The fix is a custom output style that restores thorough explanations, plus evals to catch this kind of drift on future model releases.
pablooliva.de
May 27, 2026 at 3:20 PM
Opus 4.7 is Terse
Opus 4.7's terser default style breaks down on complex projects. The fix is a custom output style that restores thorough explanations, plus evals to catch this kind of drift on future model releases.
Opus 4.7's terser default style breaks down on complex projects. The fix is a custom output style that restores thorough explanations, plus evals to catch this kind of drift on future model releases.
Thin Slices Stop /sdd-flow from Overflowing My Capacity
One-shotting features with /sdd-flow breaks down on complicated projects run in parallel. The fix: thinner vertical slices that keep oversight tight. New per-slice mode is live in the plugin.
One-shotting features with /sdd-flow breaks down on complicated projects run in parallel. The fix: thinner vertical slices that keep oversight tight. New per-slice mode is live in the plugin.
Thin Slices Stop /sdd-flow from Overflowing My Capacity
One-shotting features with /sdd-flow breaks down on complicated projects run in parallel. The fix: thinner vertical slices that keep oversight tight. New per-slice mode is live in the plugin.
pablooliva.de
May 18, 2026 at 1:38 PM
Thin Slices Stop /sdd-flow from Overflowing My Capacity
One-shotting features with /sdd-flow breaks down on complicated projects run in parallel. The fix: thinner vertical slices that keep oversight tight. New per-slice mode is live in the plugin.
One-shotting features with /sdd-flow breaks down on complicated projects run in parallel. The fix: thinner vertical slices that keep oversight tight. New per-slice mode is live in the plugin.
From One Agent to Many
Agent coordination tools now make it easy to run multiple AI agents in parallel. A look at what's available and what Trail of Bits achieved by systematizing it across an organization.
Agent coordination tools now make it easy to run multiple AI agents in parallel. A look at what's available and what Trail of Bits achieved by systematizing it across an organization.
From One Agent to Many
Agent coordination tools now make it easy to run multiple AI agents in parallel. A look at what's available and what Trail of Bits achieved by systematizing it across an organization.
pablooliva.de
April 16, 2026 at 5:54 AM
From One Agent to Many
Agent coordination tools now make it easy to run multiple AI agents in parallel. A look at what's available and what Trail of Bits achieved by systematizing it across an organization.
Agent coordination tools now make it easy to run multiple AI agents in parallel. A look at what's available and what Trail of Bits achieved by systematizing it across an organization.
Close Call, a Voice AI Sales Coach
I built an open-source voice agent for practicing sales calls against an AI customer. Runs on Pipecat + Gemini 2.5 Flash, costs $0.14 per call.
I built an open-source voice agent for practicing sales calls against an AI customer. Runs on Pipecat + Gemini 2.5 Flash, costs $0.14 per call.
Close Call, a Voice AI Sales Coach
I built an open-source voice agent for practicing sales calls against an AI customer. Runs on Pipecat + Gemini 2.5 Flash, costs $0.14 per call.
pablooliva.de
April 15, 2026 at 5:18 AM
Close Call, a Voice AI Sales Coach
I built an open-source voice agent for practicing sales calls against an AI customer. Runs on Pipecat + Gemini 2.5 Flash, costs $0.14 per call.
I built an open-source voice agent for practicing sales calls against an AI customer. Runs on Pipecat + Gemini 2.5 Flash, costs $0.14 per call.
Everything is Energy, Everything in Berlin is Beautiful
On a perfect afternoon in Berlin, everyone looked happy and oblivious. I see where the train is heading, and the accident is coming. But all crises present opportunity.
On a perfect afternoon in Berlin, everyone looked happy and oblivious. I see where the train is heading, and the accident is coming. But all crises present opportunity.
Everything is Energy, Everything in Berlin is Beautiful
On a perfect afternoon in Berlin, everyone looked happy and oblivious. I see where the train is heading, and the accident is coming. But all crises present opportunity.
pablooliva.de
April 11, 2026 at 4:18 PM
Everything is Energy, Everything in Berlin is Beautiful
On a perfect afternoon in Berlin, everyone looked happy and oblivious. I see where the train is heading, and the accident is coming. But all crises present opportunity.
On a perfect afternoon in Berlin, everyone looked happy and oblivious. I see where the train is heading, and the accident is coming. But all crises present opportunity.
Spec Driven Development Fans, You'll Love sdd-flow
A Claude Code skill that orchestrates spec-driven development through subagents: research, adversarial review, specification, implementation, code review, and critical review from a single command. Built Redakt with it in two days.
A Claude Code skill that orchestrates spec-driven development through subagents: research, adversarial review, specification, implementation, code review, and critical review from a single command. Built Redakt with it in two days.
Spec Driven Development Fans, You'll Love sdd-flow
A Claude Code skill that orchestrates spec-driven development through subagents: research, adversarial review, specification, implementation, code review, and critical review from a single command. Built Redakt with it in two days.
pablooliva.de
April 2, 2026 at 12:44 PM
Spec Driven Development Fans, You'll Love sdd-flow
A Claude Code skill that orchestrates spec-driven development through subagents: research, adversarial review, specification, implementation, code review, and critical review from a single command. Built Redakt with it in two days.
A Claude Code skill that orchestrates spec-driven development through subagents: research, adversarial review, specification, implementation, code review, and critical review from a single command. Built Redakt with it in two days.
Meet Redakt: Practical GDPR Compliance for AI Teams
Redakt is an open-source PII anonymizer built on Microsoft Presidio. It sits between employees and AI tools, replacing personal data with placeholders before prompts leave your network. No data stored, no DPA needed, fully self-hosted.
Redakt is an open-source PII anonymizer built on Microsoft Presidio. It sits between employees and AI tools, replacing personal data with placeholders before prompts leave your network. No data stored, no DPA needed, fully self-hosted.
Meet Redakt: Practical GDPR Compliance for AI Teams
Redakt is an open-source PII anonymizer built on Microsoft Presidio. It sits between employees and AI tools, replacing personal data with placeholders before prompts leave your network. No data stored, no DPA needed, fully self-hosted.
pablooliva.de
March 30, 2026 at 5:21 AM
Meet Redakt: Practical GDPR Compliance for AI Teams
Redakt is an open-source PII anonymizer built on Microsoft Presidio. It sits between employees and AI tools, replacing personal data with placeholders before prompts leave your network. No data stored, no DPA needed, fully self-hosted.
Redakt is an open-source PII anonymizer built on Microsoft Presidio. It sits between employees and AI tools, replacing personal data with placeholders before prompts leave your network. No data stored, no DPA needed, fully self-hosted.
Meet Sift: A Knowledge Base for Everything That Isn't a Note
Sift is an open source personal knowledge base that ingests any document type and makes it searchable by meaning. The story of why it exists, what went right, and what to expect.
Sift is an open source personal knowledge base that ingests any document type and makes it searchable by meaning. The story of why it exists, what went right, and what to expect.
Meet Sift: A Knowledge Base for Everything That Isn't a Note
Sift is an open source personal knowledge base that ingests any document type and makes it searchable by meaning. The story of why it exists, what went right, and what to expect.
pablooliva.de
March 27, 2026 at 6:30 AM
Meet Sift: A Knowledge Base for Everything That Isn't a Note
Sift is an open source personal knowledge base that ingests any document type and makes it searchable by meaning. The story of why it exists, what went right, and what to expect.
Sift is an open source personal knowledge base that ingests any document type and makes it searchable by meaning. The story of why it exists, what went right, and what to expect.
Agent: Do You Understand the Words Coming Out of My Mouth?
A practical checklist for making your website discoverable, readable, and citable by AI agents and answer engines — with a ready-to-paste prompt to implement it all.
A practical checklist for making your website discoverable, readable, and citable by AI agents and answer engines — with a ready-to-paste prompt to implement it all.
Agent: Do You Understand the Words Coming Out of My Mouth?
A practical checklist for making your website discoverable, readable, and citable by AI agents and answer engines — with a ready-to-paste prompt to implement it all.
pablooliva.de
March 25, 2026 at 8:34 PM
Agent: Do You Understand the Words Coming Out of My Mouth?
A practical checklist for making your website discoverable, readable, and citable by AI agents and answer engines — with a ready-to-paste prompt to implement it all.
A practical checklist for making your website discoverable, readable, and citable by AI agents and answer engines — with a ready-to-paste prompt to implement it all.
Finding Meaning in Your Notes with CK Search
CK Search adds local semantic search to any text directory, with built-in MCP server support for AI agents. A practical walkthrough of setup, configuration, and where semantic search helps — and where it doesn't.
CK Search adds local semantic search to any text directory, with built-in MCP server support for AI agents. A practical walkthrough of setup, configuration, and where semantic search helps — and where it doesn't.
Finding Meaning in Your Notes with CK Search
CK Search adds local semantic search to any text directory, with built-in MCP server support for AI agents. A practical walkthrough of setup, configuration, and where semantic search helps — and where it doesn't.
pablooliva.de
March 23, 2026 at 5:58 AM
Finding Meaning in Your Notes with CK Search
CK Search adds local semantic search to any text directory, with built-in MCP server support for AI agents. A practical walkthrough of setup, configuration, and where semantic search helps — and where it doesn't.
CK Search adds local semantic search to any text directory, with built-in MCP server support for AI agents. A practical walkthrough of setup, configuration, and where semantic search helps — and where it doesn't.
From Folders to Knowledge Base: How I Made My Notes Work for Me
A personal journey from rigid folder hierarchies to an AI-powered knowledge base — through tags, semantic search, and knowledge graphs — and why investing in how you organize information pays off in ways you can't predict.
A personal journey from rigid folder hierarchies to an AI-powered knowledge base — through tags, semantic search, and knowledge graphs — and why investing in how you organize information pays off in ways you can't predict.
From Folders to Knowledge Base: How I Made My Notes Work for Me
A personal journey from rigid folder hierarchies to an AI-powered knowledge base — through tags, semantic search, and knowledge graphs — and why investing in how you organize information pays off in ways you can't predict.
pablooliva.de
March 19, 2026 at 2:49 PM
From Folders to Knowledge Base: How I Made My Notes Work for Me
A personal journey from rigid folder hierarchies to an AI-powered knowledge base — through tags, semantic search, and knowledge graphs — and why investing in how you organize information pays off in ways you can't predict.
A personal journey from rigid folder hierarchies to an AI-powered knowledge base — through tags, semantic search, and knowledge graphs — and why investing in how you organize information pays off in ways you can't predict.
Feed the AI - Digitize Everything
AI agents are only as useful as the context you give them. Learn what it takes to build an external brain that lets AI act on your behalf — without asking every time.
AI agents are only as useful as the context you give them. Learn what it takes to build an external brain that lets AI act on your behalf — without asking every time.
Feed the AI - Digitize Everything
AI agents are only as useful as the context you give them. Learn what it takes to build an external brain that lets AI act on your behalf — without asking every time.
pablooliva.de
March 16, 2026 at 6:18 AM
Feed the AI - Digitize Everything
AI agents are only as useful as the context you give them. Learn what it takes to build an external brain that lets AI act on your behalf — without asking every time.
AI agents are only as useful as the context you give them. Learn what it takes to build an external brain that lets AI act on your behalf — without asking every time.
FolderTether: Obsidian Breaks Out of the Vault
A bidirectional link between your Obsidian notes and the folders where your actual work lives. FolderTether keeps your vault and your filesystem connected without sync, cloud, or complexity.
A bidirectional link between your Obsidian notes and the folders where your actual work lives. FolderTether keeps your vault and your filesystem connected without sync, cloud, or complexity.
FolderTether: Obsidian Breaks Out of the Vault
A bidirectional link between your Obsidian notes and the folders where your actual work lives. FolderTether keeps your vault and your filesystem connected without sync, cloud, or complexity.
pablooliva.de
March 14, 2026 at 2:49 PM
FolderTether: Obsidian Breaks Out of the Vault
A bidirectional link between your Obsidian notes and the folders where your actual work lives. FolderTether keeps your vault and your filesystem connected without sync, cloud, or complexity.
A bidirectional link between your Obsidian notes and the folders where your actual work lives. FolderTether keeps your vault and your filesystem connected without sync, cloud, or complexity.
The Notes Setup That Actually Works with AI
Why Obsidian and Markdown files turned out to be the right bet for the AI era — not for productivity reasons, but because plaintext with embedded metadata is exactly what AI agents need.
Why Obsidian and Markdown files turned out to be the right bet for the AI era — not for productivity reasons, but because plaintext with embedded metadata is exactly what AI agents need.
The Notes Setup That Actually Works with AI
Why Obsidian and Markdown files turned out to be the right bet for the AI era — not for productivity reasons, but because plaintext with embedded metadata is exactly what AI agents need.
pablooliva.de
March 13, 2026 at 3:58 PM
The Notes Setup That Actually Works with AI
Why Obsidian and Markdown files turned out to be the right bet for the AI era — not for productivity reasons, but because plaintext with embedded metadata is exactly what AI agents need.
Why Obsidian and Markdown files turned out to be the right bet for the AI era — not for productivity reasons, but because plaintext with embedded metadata is exactly what AI agents need.
Shadow AI and the Compliance Gap That Won't Close Itself
Shadow AI — employees using unapproved AI tools with company data — is creating a growing GDPR liability across Europe. Two overlapping laws apply to every AI prompt containing personal data, and most companies don't know it.
Shadow AI — employees using unapproved AI tools with company data — is creating a growing GDPR liability across Europe. Two overlapping laws apply to every AI prompt containing personal data, and most companies don't know it.
Shadow AI and the Compliance Gap That Won't Close Itself
Shadow AI — employees using unapproved AI tools with company data — is creating a growing GDPR liability across Europe. Two overlapping laws apply to every AI prompt containing personal data, and most companies don't know it.
pablooliva.de
March 12, 2026 at 7:22 AM
Shadow AI and the Compliance Gap That Won't Close Itself
Shadow AI — employees using unapproved AI tools with company data — is creating a growing GDPR liability across Europe. Two overlapping laws apply to every AI prompt containing personal data, and most companies don't know it.
Shadow AI — employees using unapproved AI tools with company data — is creating a growing GDPR liability across Europe. Two overlapping laws apply to every AI prompt containing personal data, and most companies don't know it.