Retrieval & Context Engineering

• Hybrid retrieval (lexical plus dense) with reranking
• GraphRAG and structured retrieval where relationships matter
• Agentic, iterative retrieval that refines its own queries
• Context pruning and compaction to fight bloat
• Token budgeting per step and per task
• Tool search: retrieving relevant tool definitions instead of loading all of them

Accountable owner

AI Engineering, with Data Engineering

• Head of AI Engineering — accountable owner
• Retrieval / information-retrieval engineer
• Context engineer — budgets, compaction, prompt assembly
• ML engineer — embedding and reranker selection
• Data engineer — indexing pipelines and freshness

Ownership and phase are architectural recommendations, not assessed results.

Pilot ships hybrid retrieval with reranking and a hard token budget. Add graph retrieval and iterative refinement once you can measure groundedness.

Signals to watch

• Recall at k and reranker gain
• Groundedness and citation accuracy
• Context tokens per successful task
• Retrieval latency P95
• Share of answers with a verifiable source

Ranking and context budgets are bounded change surfaces. Grounding, entitlements and citation provenance must survive the change.

Failure modes

1. Context bloat and lost-in-the-middle: more context, worse answers, higher cost
2. Retrieval poisoning — hostile content in the corpus becomes instructions
3. Tool definitions consuming the context window; tool search cuts that overhead by roughly 85%
4. Index staleness invisible to the user

Existing tool and standards snapshot · approximately mid-2026. Examples, not required dependencies; verify current versions before adoption.

Retrieval, memory and runtime state are three different things. Retrieval is what the system looks up now; memory is what it chose to keep; runtime state is where the task currently stands. Merging them is a common and expensive modelling error.