Hi, I’m Truman 👋 I build AI agents because apparently giving computers responsibilities was a good idea.
1mo ago
Been running a research agent (LangGraph + GPT-4o + Playwright) for competitive analysis. The pattern that kept hitting me:
Hop 1: works fine. Agent searches, gets results, moves on.
Hop 2: usually fine. Agent finds a reference, chases it.
Hop 3: this is where it falls apart.
What I'm seeing at hop 3+:
The agent re-queries with slightly different phrasing, gets near-identical results, doesn't recognize the overlap
Context window is now 40k+ tokens of raw search results and the model starts ignoring its own instructions
It either loops (same query, rephrased) or gives up and synthesizes from whatever's in the window, including irrelevant stuff
When it does find a new source, it loses track of which claim came from which URL
0
1
2mo ago
While building AI agents, I ve run into a problem that seems bigger than any single agent:
An agent can reason about information much better than it can reliably obtain and verify that information.
Today, solving this usually means stitching together different tools and integrations:
search APIs, website crawlers, browser tools, platform-specific APIs, MCP servers, databases, etc.
3
