Skip to content

Context engineering design canvas

Use this canvas to design the context production pipeline for an agent or RAG system. Define decisions and evidence first, then select retrieval techniques.

1. Task and decision

Field Content
Use Case
Decision the User Must Make
Goal the Agent Must Accomplish
as_of / Time Slice
Acceptance Criteria
Disallowed Outcomes
Maximum Retrieval Rounds
Deadline and Cost Budget

2. Context inventory

Type Required Information Source Owner Lifecycle Included in Model
Environmental Runtime
Task & Goal Task
Historical / Memory Thread / Cross-conversation
Agent State Run
Orchestration Task Graph
Temporal Event / Valid Time
Policy & Normative Versioned

For each context item, also answer:

  • Is the source authoritative?
  • Who may write, correct, and delete it?
  • Do the user, the agent, and the current purpose have read access?
  • When does it expire?
  • Are alternative versions available?
  • How should it be compressed or omitted when over budget?
  • Does it need to enter the Model Context, or only the Tool Runtime?

3. Source manifest

source_id:
source_type: doc | git | db | api | graph
owner_team:
classification:
acl_policy:
refresh_sla:
valid_time_field:
deletion_mode:
parser_version:
schema_version:

Minimum fields for indexed objects

  • source_id
  • source_version
  • content_hash
  • observed_at
  • valid_time
  • acl_labels
  • parser_version
  • locator

4. Evidence contract

evidence_id:
source_id:
source_version:
locator:
content:
claims_supported:
  -
observed_at:
valid_time:
  from:
  to:
access_label:
retrieval_scores:
transformations:
content_hash:

Checks:

  • Evidence can be traced back to the original source;
  • The time range covers the Claim to be supported;
  • Authorization is enforced before data is returned;
  • Compression and redaction steps are visible;
  • Deletions or corrections can propagate.

5. Retrieval plan

question:
intents:
  -
entities:
  - type:
    id:
time_scope:
  from:
  to:
  as_of:
channels:
  - fts
  - vector
  - graph
  - sql
  - api
filters:
required_graph_paths:
evidence_requirements:
  -
max_rounds:
deadline:
token_budget:
termination:
  no_progress_rounds:
  on_missing_evidence: partial

Query shapes and channels

Query Shape Preferred Channel
IDs, error codes, and exact terms FTS / BM25
Synonymous expressions, concepts, and descriptions Vector
Ownership, dependencies, paths, and impact scope Graph
Counts, groupings, and time windows SQL / Analytics
Current orders, deployments, or inventory Operational API / DB

6. Context pack manifest

pack_id:
task_id:
purpose:
as_of:
instruction_version:
goal_ref:
state_version:
evidence:
  - evidence_id:
tools:
  - name:
    version:
omissions:
  - candidate:
    reason:
token_allocation:
  instructions:
  task_state:
  evidence:
  tools:
  response_reserve:
built_at:
builder_version:
pack_hash:

Pack invariants

  • Relevant: every item serves the current task;
  • Authorized: the user, agent, and use are permitted access;
  • Timely: satisfies as_of, validity periods, and Freshness requirements;
  • Traceable: includes Source, Version, and Locator;
  • Budgeted: selected according to policy, with no random truncation;
  • Evaluable: the Pack can be saved, replayed, and compared.

7. Graph query guard

Control Configuration
Node Allowlist
Relationship Allowlist
Allowed Directions and Path Templates
Maximum Hop Count
LIMIT
Query Timeout
Read-Only Transaction
Tenant / Object ACL
Valid Time Conditions
Cost Limit
Return Schema

8. Context trace

Record at least:

  • source_discovered
  • retrieval_executed
  • candidate_rejected
  • evidence_transformed
  • pack_built
  • claim_generated
  • answer_validated

Each rejection event should include the Candidate ID, reason, policy, or alternative version.

9. Layered evaluation

Retriever

  • Required Evidence Recall:
  • Exact Match Recall:
  • Multi-hop Path Accuracy:
  • Temporal Retrieval Accuracy:

Context pack

  • Context Precision:
  • Provenance Completeness:
  • Freshness Accuracy:
  • ACL Violation Rate:
  • Token Efficiency:
  • Compression Fidelity:

Answer

  • Claim Evidence Coverage:
  • Faithfulness:
  • Citation Correctness:
  • Epistemic Status Accuracy:
  • Missing Evidence Disclosure:

10. Fault injection

  • Vector retrieval returns an outdated version with high similarity;
  • The correct evidence falls outside the original Top-k;
  • A Graph relationship lacks valid_to;
  • A document contains indirect Prompt Injection;
  • The Pack exceeds its budget;
  • The compressor removes a negation, monetary amount, or time reference;
  • The current user may view only a redacted summary;
  • Two sources present conflicting conclusions;
  • A deleted document remains in a cache or Memory;
  • Dynamic retrieval produces no new evidence for two consecutive rounds.

11. Release gates

  • 100% of critical Claims are bound to Evidence IDs;
  • ACL Violation Rate is 0;
  • Outdated, future-version, and deleted evidence cannot enter the Pack;
  • Graph queries satisfy Schema, Hop, time, and cost constraints;
  • The Pack can be saved and replayed;
  • Retriever, Pack, and Answer failures can be isolated independently;
  • Dynamic retrieval has round, time, cost, and no-progress termination limits;
  • Benefits over a simple two-step RAG pipeline have been quantified.