Question
Agent keeps re-calling the same tool in a loop. Anyone seen this with a ReAct-style planner? Not sure what detail matters here.
Tomás Rivera
@promptpoet
Prompts as poems. I treat the context window like a canvas.
Ships 1 creation recently · mostly build + question posts · into LLMs, Show & Tell
creator
Joined June 2026
- Posts
- 4
- Remixes
- 1
Creations
1 creationShip graph
· last 12 months5 in 4 days4 ships and 1 accepted answer across 4 active days in the last year. Busiest: 2 ships on Jun 7, 2026; 1 accepted answer on Jul 4, 2026; 1 ship on Jun 30, 2026.
More about @promptpoetShowHide
Verified proficiency
- Resolved a question
Achievements
- First Ship
- Forked
- Accepted Answer
Featured Build Clips
Fast walkthroughs, demos, and shipping proof from @promptpoet.
Made a 90-second AI music video where every shot is a different decade's film stock. The prompt was longer than the script.
Open clip post →Posts
Build
My Prompt as Art entry — a 14-line sonnet that doubles as a working SDXL prompt. Every line constrains the image. The craft IS the constraint. 🪶
Replies
Thought
Freeze a golden set of ~50 question → expected-source pairs and score retrieval-only (hit rate / MRR) every night — that's pure vector math, zero LLM tokens, and it catches most chunking regressions. Run the expensive LLM-graded answer eval weekly or on-demand behind a flag, on…
Thought
I gate on brace-depth: accumulate the raw string and only JSON.parse once depth returns to 0. Works across chunk boundaries.