Pebellslearn by building
0%
RoadmapsMatrixCoursesSandboxSign in
Agent Memory  ›  Lesson

Short-Term Memory — Keeping the Working Context Lean

Summarization / Compression 12 minShort-term memory is the working context of a task, kept useful by trimming tool results, sliding windows and summarization while pinning goals, constraints, decisions and exact identifiers.

Short-Term Memory — Keeping the Working Context Lean

Planning a three-city trip, Tripmate makes 30 tool calls. Each train search returns a big block of text, and by call 25 the context is nearly full, every call is slow and expensive, and the model starts overlooking details. Short-term memory is the working context of one task, and it needs managing like a desk that keeps filling up.

The rule

Keep the goal and the decisions; shrink the raw material.

Short-term memory is everything carried from turn to turn inside the context window: the instructions, the conversation, the plan, and tool results. Three techniques keep it useful:

  • Trimming — cut tool results down to what matters before storing them. Fifteen trains with every stop become the three candidates, with times and fares.
  • Sliding window — keep the most recent turns in full and drop older ones. Simple, but anything important from early on must be saved separately first.
  • Summarization (compression) — replace a long stretch of old turns with a short summary written by the model: decisions made, facts learned, open questions.

What must survive every cut:

  • the user's goal and constraints (dates, budget, "vegetarian"),
  • decisions already made ("Pune → Jaipur leg: booked the Friday sleeper"),
  • what is still open ("Jaipur → Udaipur leg: not yet searched").

A healthy working context often has three layers:

[pinned] Goal: Pune → Jaipur → Udaipur → Pune, 15–22 Oct, ₹8,000 total, vegetarian
[summary] Leg 1 booked (Friday sleeper, ₹1,180). Leg 2 options: 2 trains shortlisted.
[recent]  last 6 turns in full

The shortcut

Before anything enters the context, ask: "Will the next decision need this exact text, or just its conclusion?" Just the conclusion → store the conclusion. Most raw tool output falls in that bin.

Compressing the first legStep 1 of 4
  1. Before

    Turns 1–12: the request, four searches of about 2,000 tokens each, a comparison, a booking. Around 12,000 tokens.

The trap is summarising away something that turns out to matter, such as a booking reference. Pin exact identifiers, numbers and constraints verbatim; summarise only the reasoning and chatter around them.

Drills

Answer fast — trust the rule.

quick drill

Which technique replaces old turns with a short written recap?

quick drill

What is the main risk of a plain sliding window?

quick drill

Which detail should be kept word-for-word, not summarised?

quick drill

A search returned 15 trains; Tripmate needs only the 3 that fit. What should enter the history?

Remember

  • Short-term memory is the working context: keep goals, constraints and decisions; shrink raw material.
  • Shortcut: does the next decision need this exact text, or just its conclusion?
  • Trap: summarising away exact values — pin IDs, numbers and constraints verbatim.

Practice — level up

0/1 solved

Write your answer, then compare it with a rubric and a model answer.

ExplainCompress a long history

Tripmate's context for a three-city trip is nearly full. Explain how you would compress it, what must survive word-for-word, and what can be summarised or dropped.