Pinned Tweet
It's Dosu Drop Day! 🎃
Dosu answers with live context from connected MCP servers like Sentry, Datadog, GitHub, and Confluence. Connect one to a Library with MCP Tools (beta), starting with read-only credentials.
go.dosu.dev/drop-oct26-x
From Prototype To Production Agents That Remember nitter.cf/i/broadcasts/1AxRnZQjn…
Should Humans Review An AI Agent's Work?
Our CEO's, Devin Stein, take: people are already overwhelmed with review. Reviewing small pieces of conflicting information is work nobody has time for. Human approval can help build trust early on, but knowledge that exists for agent performance should be maintained by agents end to end.
What matters most is a self-correcting loop, so the system recovers even when it isn't perfect.
From our fireside chat with @Pydantic. Recording and transcript in the comments 👇
Dosu retweeted
Field journal, vol. 01 📓 AGNTCon + MCPCon, San Jose!
So far it's rain, palms, a full room for @dexhorthy's State of the Software Factory, a Bigfoot and a glazed T-rex.
Here through Friday. Building agents or MCP? Say hi and let’s talk! 👋 😄
We rebuilt the agent behind Dosu's answers. In the week after the switch, median Library searches per GitHub answer rose from 4 to 7, and Dosu's slowest answers arrived about half a minute sooner in Slack and on GitHub.
With the Dosu CLI, Claude Code and recent Codex releases load Dosu's own MCP tools at session start.
Security review blocking a hosted trial? Ask about a limited self-hosted trial. Coding agents stuck on the same steps? Ask about a design partnership.
go.dosu.dev/drop-oct26-x
In our @vercel AI SDK replays, agents learned the same build rule across 59 sessions and 40 issues. We traced the repeated discoveries via @anthropicAI's Claude Code and @openai's Codex logs. What do your agents keep relearning? go.dosu.dev/session-memory-x
ALT Dosu studies an open glowing grimoire in a vast, candlelit cathedral library while enchanted pages float toward a moonlit stained-glass window.
We replayed 49 @vercel AI PRs across two coding agents, with an estimated $44.00 on Claude Code (Opus 5.5) and $27.29 on Codex (GPT 6.1 Sol).
Where did the gap come from? Spoiler: Low- and mid-scope work came out about even...
go.dosu.dev/agent-cost-gap-x
A working test command becomes a reusable procedure when the next coding agent knows when to run it and how to confirm the suite ran. We walk through make test-int, shared repository instructions, and skills. dosu.dev/blog/procedural-mem…
Does your coding agent still recommend a tool your team replaced? We found a Celery migration comment that survived the move to DBOS and the removal of Celery. Semantic memory needs to preserve when a fact no longer applies. dosu.dev/blog/semantic-memor…
Your agent remembers “run make test-int.” The session explaining that it starts the test database may already be gone.
Check how Claude Code and Codex store session history, and whether you can trace a saved instruction to its source.
go.dosu.dev/episodic-memory-…