Lesson 1696 of 2116
Agentic AI: state vs context — what to write down
Context is what the agent sees this turn. State is what persists. Confusing them produces forgetful agents and bloated prompts.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1The premise
- 2agent state
- 3context window
- 4memory design
Concept cluster
Terms to connect while reading
Section 1
The premise
Agents need durable state (facts that outlive a turn) separate from working context (what's loaded into the prompt right now). Mixing the two creates either amnesia or context overflow.
What AI does well here
- Read from a state store you provide as a tool
- Write structured facts when given a write tool
- Summarize prior turns when asked to compact
What AI cannot do
- Remember anything across runs without external state
- Decide what's worth persisting without rules
- Keep state consistent across parallel agents
Key terms in this lesson
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “Agentic AI: state vs context — what to write down”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 40 min
Setting Context-Window Budget Policies for Long-Running Agents
How to keep an agent's context window from filling with noise mid-run.
Builders · 7 min
Memory vs context window: what your agent remembers
Your agent forgets between sessions unless you give it actual memory — not just a longer context window.
Creators · 48 min
Computer Use API: Letting AI Click Through GUIs
Computer Use lets Claude see your screen and use it — mouse, keyboard, apps. The capability is real, the gotchas are real. A hands-on look at what works in 2026.