Agentic Context Engineering

Agentic Context Engineering is the discipline of deciding what the model is allowed to see for a specific run, then making that decision reproducible.

It is not prompt writing. A prompt is one output of the Context plane. The real artifact is the CompiledContext: the bounded prompt plus the manifests, controls, omissions, source versions, and budget report that explain how it was produced.

Definition

Agentic Context Engineering turns a versioned Context Pack, a RunContext, and runtime evidence into a CompiledContext envelope.

The envelope must answer four questions:

If those artifacts are missing, the system may still be using good prompts, but it is not doing ContextOS-grade context engineering.

Why It Exists

Enterprise agents fail when context assembly is informal:

• Policy is copied into prompts and quietly goes stale.
• Tool availability is implied rather than bound to identity and approval mode.
• Retrieval injects evidence without provenance, freshness, or access scope.
• Memory writes return as future context before consent or promotion.
• Token pressure silently drops the facts needed for an auditable decision.

The Context plane makes context assembly explicit. It lets the Decision plane reason over a known input envelope and lets the Trust plane replay the run later.

Compiler Contract

The Context Pack Compiler follows the same eight-stage shape used in How It Works:

The compiler may use model assistance for classification, summarization, or compression, but the final envelope must still be typed, versioned, and traceable.

Context Buckets

ContextOS uses buckets so teams can reason about pressure and governance consistently.

Working state that only belongs to the current turn should remain session state. Durable recall belongs in memory only after the Memory Model promotion rules allow it.

CompiledContext Shape

The implementation guide owns the full schema. A useful mental model:

{
  "compiled_context_id": "cc_run_refund_001",
  "run_id": "run_refund_001",
  "pack_ref": "ctxpack.support@1.0.0",
  "compiled_prompt_ref": "sha256:...",
  "manifests": {
    "policy": ["POLICY_RETURNS_V1:R_HIGH_VALUE_REQUIRES_APPROVAL"],
    "tools": ["adp_orders.lookup", "adp_payments.issue_refund"],
    "evidence": ["kg:order:ord_881#snapshot_2026_05_09"],
    "memory": [],
    "omissions": [
      {
        "bucket": "session",
        "reason": "budget_pressure",
        "source_ref": "msg_older_than_window"
      }
    ]
  },
  "runtime_controls": {
    "max_tool_calls": 8,
    "max_replan_attempts": 2,
    "approval_gates_active": ["GATE_FINANCE_APPROVAL"],
    "must_refuse": [],
    "must_escalate": ["fraud_signal_high"]
  },
  "budget_report": {
    "limit_tokens": 12000,
    "used_tokens": 7420,
    "truncated": true
  }
}

Quality Signals

Context quality is not a vibe. The compiler should emit signals that can be scored later:

These signals feed Evaluation and Observability and the Improvement Loop. They should be stored as diagnostics, not hidden in logs.

Autotune surfaces

The Context plane is the safest first place to apply autotune because many changes are bounded, replayable, and reversible. A Context Pack may declare tunable surfaces, but the compiler must refuse proposals outside that declaration.

Every candidate should produce a TuningProposal that names the target intent, target metric, baseline pack, replay sets, expected scorecard delta, and rollback target. The Context plane does not promote the candidate; the Trust plane gates it through replay, review, and staged rollout.

Boundary With Adjacent Pages

Agentic Context Engineering is the discipline. The Context Pack Compiler is the component. The Context Pack is the source artifact. CompiledContext is the runtime artifact.

Failure Modes

Operational Metrics

• Context compile latency by stage.
• Required evidence coverage.
• Omission rate by bucket and reason.
• Tool manifest eligibility mismatch rate.
• Policy manifest evaluation error rate.
• Replay match rate for CompiledContext reconstruction.
• Budget pressure by intent and pack version.
• Decision quality delta after context-pack changes.

Example

For support.refund, the compiler should include:

• the active refund policy bundle,
• the eligible read and refund tools,
• order and customer evidence refs,
• the support.refund.execute decision binding,
• GATE_FINANCE_APPROVAL when the amount exceeds INR 3000,
• a budget report showing whether any evidence or session state was compressed.

The Planner can then propose work against a known envelope. The Critic can reject a plan if required context is missing before the refund tool is ever called.

Common Misconceptions

• “Better prompts solve context.” Better prompts help, but governance comes from typed inputs, manifests, and replay.
• “Retrieval is the Context plane.” Retrieval is one input. The Context plane also resolves policy, tools, memory, budgets, and controls.
• “Summaries are always safe compression.” Summaries must carry source refs, transformation metadata, and quality signals.
• “The model can decide which policy matters.” Policy selection and enforcement happen outside model discretion.

Related Docs

• Context Pack
• Cognitive Core
• Knowledge Graph
• Memory Model
• Evaluation and Observability