L3 Context and memory
Working plan
Keeps the agent's current plan, such as its to-do list, in its own saved place and shows it to the model on every turn.
Why it matters
Long tasks outlast the conversation's room, so old turns get summarized or cut and the plan written there is lost. A plan saved apart from the conversation and shown again on every turn keeps the agent on track through summaries and restarts. Giving the agent a to-do list to write, and the plan mode, are the Planning tools topic; this one keeps that plan in view.
What to build
Session plan record rendered at request tail
The default the research recommends. The reasoning and the code behind it are in the app.
What it takes, by kind of agent
- Conversational assistantMust-have
- CodingMust-have
- Deep researchMust-have
- Browser/GUIMust-have
How well it is studied
- Harnesses checked
- 30
- Checked facts behind it
- 305
See the 305 checked facts and how each harness does it
The facts, the code lines they come from and the rules for this topic are in the app. Sign in with Google; new accounts are approved by hand.
Also in L3 Context and memory
- CompactionSettled practice
Shrinks the conversation before it overflows the model's context window, without losing what the agent must remember.
- Assistant Must-have
- Coding Must-have
- Research Must-have
- Browser Must-have
- Result clearingSettled practice
Keeps large tool outputs out of the conversation while leaving the full text one request away.
- Assistant Must-have
- Coding Must-have
- Research Must-have
- Browser Must-have
- External memorySettled practice
Keeps what the agent must remember outside its context window and brings back only what matters for the request.
- Assistant Must-have
- Coding Optional
- Research Must-have
- Browser Not applicable
- Retrieval qualityOpen problem
Finds the few passages that answer a question and gives each one an id the answer can cite.
- Assistant Must-have
- Coding Not applicable
- Research Must-have
- Browser Not applicable