Taylor Dolezal
Head of OSS at Dosu · 18 posts
How 20 Vercel AI SDK tickets drove the agent cost gap
Claude Code on Opus 5.5 and Codex on GPT 6.1 Sol attempted the same 49 tickets. The recorded cost gap came entirely from high-scope work.
Taylor DolezalHead of OSSProcedural Memory for Coding Agents: Turning Knowledge Into Action
Learn how to turn a coding agent's discovery into a shared procedure, choose where the instructions belong, and check that the next agent uses them correctly.
Taylor DolezalHead of OSSSemantic memory for coding agents needs a history
Your coding agent needs to know which facts still apply. Our Celery-to-DBOS migration shows why semantic memory needs scope, dates, and source evidence.
Taylor DolezalHead of OSSEpisodic memory for coding agents: What survives your sessions
Episodic memory is a coding agent's record of past sessions. Saved lessons can outlive the transcripts behind them, so keep each lesson tied to its source.
Taylor DolezalHead of OSSHow to design a CLI login flow for coding agents
Design a CLI login for coding agents with a ticket flow that pauses, resumes in a new process, and returns the next command in JSON. Learn how Dosu built it.
Taylor DolezalHead of OSSYour coding agent budget pays for context, not code
Planning and gathering context account for two thirds of agent costs.
Introducing Decant: Insights for your Claude Code and Codex sessions
Claude Code and Codex log every session you run. Decant turns those logs into real numbers for what your agents did and how much it cost, without leaving your machine.
Taylor DolezalHead of OSSAutomate recurring work with Dosu Templates
Turn recurring, judgment-heavy work like release notes, status updates, and triage into a reusable Dosu Template that Dosu drafts from your connected sources.
Taylor DolezalHead of OSSA stale AGENTS.md is worse than no AGENTS.md
Cloudflare built an internal platform to keep AGENTS.md files fresh across thousands of repos. Here are the methods to keep yours current, and how we do it at Dosu.
Taylor DolezalHead of OSSHow Fresh Are Your Docs? Score Documentation Freshness in CI
A 0-100 freshness signal that catches documentation drift in CI on every PR. Three deterministic checks plus a Claude Code semantic layer for the gray zone.
Taylor DolezalHead of OSSIntroducing better-stale-bot, an AI GitHub Stale Bot That Reads First
Meet better-stale-bot, an open source GitHub stale bot alternative that reads inactive issues, summarizes context, and closes only when the thread supports it.
Agentic Infrastructure: What We Learned Hosting a Panel With LanceDB, CodeRabbit, and CrewAI
Four companies focused on agentifying their tech stack. One rewrote its codebase for AI. Another found PII leaking through OpenTelemetry traces.
A Claude Code Skill for Auto-Generating Project Docs
Generate your project's entire documentation layer from source code with a single Claude Code skill. Build /doc-it and run it against a real FastAPI project.
Taylor DolezalHead of OSSHow to Catch Documentation Drift with Claude Code and GitHub Actions
Let's craft a GitHub Actions workflow with Claude Code that helps to catch stale docs as you iterate on your code.
Taylor DolezalHead of OSSBluefin: Community Support After StackExchange
Bluefin cut support response times from 42 hours to 12 minutes by using Dosu across six repositories.
Taylor DolezalHead of OSSWhat tldraw and goose Are Teaching Us About AI-Ready Open Source
Two open source projects face the same AI contribution crisis and make different choices. Both were right.
Taylor DolezalHead of OSSHow Dosu Powers CNCF’s Community Knowledge Platform
CNCF launched ask.cncf.io with Dosu at KubeCon NA 2025, answering 765 questions to help attendees navigate 200+ cloud native projects.
Taylor DolezalHead of OSSHow IBM Research’s Docling Manages Open Source Growth with Dosu
IBM's Docling scaled from 0 to 40K GitHub stars (as of October 2025) in one year with just 4 maintainers. Check out how Dosu reduced response time by 99% and automated 70% of issues.
Taylor DolezalHead of OSS