Organizational Context for AI Coding Agents with Dennis Pilarinos
Episode
49 min
Read time
2 min
Topics
Remote Work, Startups, Artificial Intelligence
AI-Generated Summary
Key Takeaways
- ✓Context conflict resolution: When Slack, Jira tickets, and source code contradict each other, treat the source code as the highest-weight truth signal, then use pull request diffs as secondary breadcrumbs. Unblocked's engine performs runtime conflict resolution across all connected data sources rather than relying on static, pre-indexed snapshots.
- ✓Permission-aware AI systems: AI context engines must enforce access control at query runtime, not at indexing time. Unblocked demonstrates this with a live demo: revoking a user's Google Doc access causes the system to immediately stop surfacing that document's contents, preventing privilege escalation through AI intermediaries.
- ✓Pull request enrichment: Most developers write minimal PR descriptions, leaving organizational knowledge underutilized. Unblocked automatically diffs every pull request in connected repositories and builds a background knowledge graph from those diffs, upgrading low-quality documentation into a queryable institutional memory without requiring any manual effort from engineering teams.
- ✓Planning before agentic execution: Teams using Unblocked's context engine during the planning phase — before agents write any code — produce significantly better implementation plans because the agent already knows coding standards, architectural decisions, and common code review failure points, eliminating rework cycles that would otherwise surface during pull request review.
- ✓Slack integration as primary adoption vector: Unblocked monitors engineering support channels and responds to developer questions within seconds when confidence is high. Across tens of thousands of user feedback responses, 95% report the tool as helpful, with roughly half of the remaining 5% simply refusing to answer surveys rather than indicating dissatisfaction.
What It Covers
Dennis Pilarinos, founder of Unblocked, explains how the primary bottleneck in AI-assisted software development has shifted from code generation to context — specifically, aggregating organizational knowledge from Slack, pull requests, Notion, source code, and production telemetry to give both developers and coding agents decision-grade information.
Key Questions Answered
- •Context conflict resolution: When Slack, Jira tickets, and source code contradict each other, treat the source code as the highest-weight truth signal, then use pull request diffs as secondary breadcrumbs. Unblocked's engine performs runtime conflict resolution across all connected data sources rather than relying on static, pre-indexed snapshots.
- •Permission-aware AI systems: AI context engines must enforce access control at query runtime, not at indexing time. Unblocked demonstrates this with a live demo: revoking a user's Google Doc access causes the system to immediately stop surfacing that document's contents, preventing privilege escalation through AI intermediaries.
- •Pull request enrichment: Most developers write minimal PR descriptions, leaving organizational knowledge underutilized. Unblocked automatically diffs every pull request in connected repositories and builds a background knowledge graph from those diffs, upgrading low-quality documentation into a queryable institutional memory without requiring any manual effort from engineering teams.
- •Planning before agentic execution: Teams using Unblocked's context engine during the planning phase — before agents write any code — produce significantly better implementation plans because the agent already knows coding standards, architectural decisions, and common code review failure points, eliminating rework cycles that would otherwise surface during pull request review.
- •Slack integration as primary adoption vector: Unblocked monitors engineering support channels and responds to developer questions within seconds when confidence is high. Across tens of thousands of user feedback responses, 95% report the tool as helpful, with roughly half of the remaining 5% simply refusing to answer surveys rather than indicating dissatisfaction.
Notable Moment
Pilarinos tested his own product by letting Claude Code handle secrets management without context — it chose a method that would expose credentials immediately upon infrastructure compromise. Unblocked's code review caught the error and recommended vault-based encryption, which Pilarinos then delegated back to the agent to fix autonomously.
Episode Transcript
AI agents have taken on a growing share of software development work, so much so that the hardest problems are shifting away from cogeneration towards something new. Context. The challenge is now contextualizing why systems work the way they do, how architectural decisions were made, and the sources of truth that exist outside of the code base. As teams adopt agentic tools, gaps or inconsistencies in context have emerged as a primary reason why software fails to meet production standards. Unblocked is a startup focused on solving this context gap. Their context engine aggregates and reasons over organizational knowledge spread across source code, pull requests, documentation, chat systems, and production telemetry. By acting as a context engine for both developers and AI agents, Unblocked aims to improve AI code quality and review, reduce interruptions, accelerate onboarding, and enable safer, more effective agentic workflows. Dennis Pilorinos is the founder and CEO of Unblocked. Previously, he helped build Azure at Microsoft, worked at AWS, and cofounded BuddyBuild, which is a mobile CI platform acquired by Apple. Dennis joins Kevin Ball to discuss context engineering, reconciling conflicting sources of truth, permission aware AI systems, the shifting bottlenecks in the software development life cycle, and what it means to be a software engineer in an increasingly agentic world. Kevin Ball or k Ball is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He cofounded and served as CTO for two companies, founded the San Diego JavaScript Meetup, and organizes the AI in action discussion group through Latent Space. Check out the show notes to follow Keball on Twitter or LinkedIn, or visit his website, keball.llc. Dennis, welcome to the show. Thanks very much. Thanks for having me. Yeah. I'm really excited to learn about what you're up to. But let's start a little bit with you. So can you give our listeners a little bit of your background and what led to Unblocked? Sure. I'm Dennis Pilrinos. I'm the founder and CEO of Unblocked. I've been building developer tools for the better part of twenty years. My career started in earnest at Microsoft, where I was one of the earliest people to think about shifting on premise computing APIs to cloud hosted APIs. So it was part of the team that built a lot of the Azure platform. I worked in AWS. I started a company called BuddyBuild, which is a CI platform for mobile app developers, which is acquired by Apple. So about three years after we started it, I've worked at Apple for about a year and a half. And basically through that series of, like, lived experiences and life experience, we took a lot of that to go and build Unblocked. And so Unblocked helps engineers get the context that they need to get their jobs done. So that's really kind of my background and a little bit about what we're trying to do at Unblocked. Yeah. So let's talk about that word …
Get the full transcript (9,949 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 46-minute episode.
Get Software Engineering Daily summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from Software Engineering Daily
SED News: The NVIDIA-Hugging Face Deal, China’s Proxy Economy, the Open Weight Surge
Sep 8 · 52 min
20VC (20 Minute VC)
20VC: Anj Midha on Investing $300M into Anthropic | The Early Days of Anthropic & How 21 of 22 VCs Turned it Down | The Four Bottlenecks to Compute | What the China Has Smashed and Why We Should Be Worried
Apr 14
More from Software Engineering Daily
Moving Beyond RAG with Precomputed Context
Sep 3 · 55 min
a16z Podcast
Why Every Satellite Needs Earth | Northwood CEO on a16z
Mar 23
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
by Anthropic
“Pilarinos tested his own product by letting Claude Code handle secrets management without context — it chose a method that would expose credentials immediately upon infrastructure compromise.”
company
- UnblockedBy guest
“Dennis Pilarinos, founder of Unblocked, explains how the primary bottleneck in AI-assisted software development has shifted from code generation to context”
More from Software Engineering Daily
We summarize every new episode. Want them in your inbox?
SED News: The NVIDIA-Hugging Face Deal, China’s Proxy Economy, the Open Weight Surge
Moving Beyond RAG with Precomputed Context
The Death of Online Anonymity
TypeScript 7 and What Comes Next
The Gap Between AI Spending and AI Value
Similar Episodes
Related episodes from other podcasts
20VC (20 Minute VC)
Apr 14
20VC: Anj Midha on Investing $300M into Anthropic | The Early Days of Anthropic & How 21 of 22 VCs Turned it Down | The Four Bottlenecks to Compute | What the China Has Smashed and Why We Should Be Worried
a16z Podcast
Mar 23
Why Every Satellite Needs Earth | Northwood CEO on a16z
This Week in Startups
Mar 16
Are Brain-Computer Interfaces Actually Ready for Humans?
The Nathan Barry Show
Mar 5
Live Coaching: How We're Growing This Business To $5M | 118
The Bio Report
Jan 28
A Billion-Dollar Bet on AI-First Drug Development
Explore Related Topics
This podcast is featured in Best Cybersecurity Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's Startups & Product Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into Software Engineering Daily.
Every Monday, we deliver AI summaries of the latest episodes from Software Engineering Daily and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime