L3 Context and memory
Result clearing
Keeps large tool outputs out of the conversation while leaving the full text one request away.
Why it matters
Every turn resends the whole conversation, so a large output kept inline is paid for again and again and soon overflows the model's working space. Trimming it early, and clearing old results without breaking the record of calls, keeps runs cheap while the agent can still get the detail back.
What to build
Spill oversized results and point to them
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
- 386
See the 386 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
- Working planOpen problem
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.
- 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