EU AI Act high risk obligations are now enforceable. Check your exposure
Insights About us Careers
Contact us
AI Agents & Agentic Automation

Agentic RAG

Retrieval that plans before it searches, decomposes a hard question into answerable parts, checks what it found and searches again when the evidence is thin, for the questions single-shot retrieval simply cannot reach.

6 to 10 weeks
Typical build
Fixed scope
Commercial model
Verified
Before answering

Standard retrieval answers questions whose answer sits in one place. Ask it something that requires comparing two contracts, tracing a change across three policy versions, or checking whether a stated condition actually holds, and it retrieves the most similar-looking passages and produces something confident. Agentic RAG exists for those questions, and it costs more, which is why it should be used deliberately.

In one paragraph

Agentic RAG is retrieval augmented generation in which the system plans its own retrieval: decomposing a question into sub-questions, choosing which sources to search, evaluating whether the evidence gathered is sufficient, searching again where it is not, and verifying the answer against the retrieved material before returning it.

When single-shot retrieval is not enough

  • Multi-hop questions. The answer requires a fact from one document to locate the relevant part of another.
  • Comparison. Two or more sources have to be retrieved and contrasted, not summarised together.
  • Aggregation. The answer is a count, a total or a pattern across many documents rather than a passage in one.
  • Temporal reasoning. Which version applied at a particular date, and what changed between versions.
  • Conditional questions. Whether a rule applies to a specific case, which requires checking the rule and the case separately.

For everything else, and it is usually the majority of traffic, single-shot retrieval is faster, cheaper and easier to reason about. We build both and route between them, because paying agentic prices for a simple lookup is a design error rather than a sophistication.

How agentic RAG works in practice

Plan before retrieving

The system classifies the question, decides whether it needs decomposition at all, and where it does, produces an explicit plan of sub-questions and the sources each should be answered from. The plan is visible in the trace, which is what makes the behaviour debuggable rather than mysterious.

Retrieve per sub-question, with the right tool

Different sub-questions want different retrieval: semantic search over policy text, a filtered query over structured records, a lookup by identifier. Each becomes a scoped tool, so retrieval strategy is a tool-selection problem with the same discipline as any other, as covered under tool and function-calling integration.

Judge sufficiency, then stop or continue

After each round the system assesses whether the evidence answers the sub-question. Thin evidence triggers a reformulated search; repeated failure triggers an honest 'not found in the sources available' rather than an inference dressed as a finding. A hard ceiling on rounds keeps cost and latency bounded.

Verify the answer against the evidence

Before returning, each claim is checked against the passages retrieved, and unsupported claims are removed or flagged. This verification pass is the single most valuable component in the design, and it is what makes agentic RAG defensible for legal, compliance and clinical use.

Route by question type

A classifier sends straightforward questions down the fast single-shot path and reserves the agentic path for questions that need it. Most deployments end up with the majority of traffic on the cheap path, which is what makes the whole thing affordable.

Worth knowing

The foundation still has to be good

Agentic retrieval magnifies whatever the underlying index gives it: better recall means better plans, and a weak index means several expensive rounds of finding nothing. We measure and fix baseline retrieval first, as set out in RAG system development, before adding a planning loop on top of it.

What it costs, and what it buys

DimensionSingle-shot RAGAgentic RAG
LatencyTypically one to three secondsSeveral seconds to tens of seconds
Cost per questionOne retrieval, one generationSeveral retrievals, planning and verification
Multi-hop accuracyPoor, and confidently soMaterially better, and traceable
ExplainabilityWhich passages were usedThe plan, each search, and the sufficiency judgement
Failure modeA fluent wrong answerAn explicit 'not found', more often than not

That last row is why the extra cost is worth paying for high-stakes questions. A system that says it could not find the answer is far more useful to a professional than one that invents a defensible-sounding paragraph.

Process

How the engagement runs

Baseline retrieval is fixed first, then the planning layer is added only where the score says it is needed.

Weeks 1 to 2

Question taxonomy and baseline

Real questions classified by type, single-shot baseline measured per type, and the subset that genuinely needs planning identified.

Weeks 3 to 4

Retrieval tools

Sub-question retrieval built as scoped tools across your sources, each measured independently.

Weeks 5 to 7

Planning and verification

Decomposition, sufficiency judgement, bounded iteration and the verification pass, scored against the multi-hop set.

Weeks 8 to 9

Routing and cost control

Classifier routing traffic between fast and agentic paths, with latency and cost per question type measured.

Week 10

Handover

Evaluation sets, traces, routing thresholds and the runbook for tuning them as question patterns change.

Deliverables

What you receive

A system that answers the hard questions and is honest about the ones it cannot.

01

Question taxonomy

Real questions classified by type with the baseline score for each, showing where planning is justified.

02

Agentic retrieval pipeline

Planning, sub-question retrieval tools, bounded iteration and sufficiency judgement.

03

Verification layer

Claim-level checking against retrieved evidence, with unsupported claims removed or flagged.

04

Routing layer

Classifier and thresholds sending each question down the cheapest path that answers it.

05

Evaluation suite

Multi-hop and comparison cases with correct answers and acceptable evidence, wired into CI.

06

Cost and latency profile

Per question type, with the levers available if the mix shifts.

Fit check

Is this the right engagement?

Worth being direct. Agentic RAG is the wrong spend in some situations, and those are listed rather than buried.

Good fit if

  • Users ask comparison, multi-hop or conditional questions that current retrieval answers badly.
  • A confident wrong answer carries real professional or regulatory consequence.
  • Answers must show not just sources but how the conclusion was reached.
  • Baseline retrieval is already decent and the remaining failures are structural rather than about recall.
  • Several seconds of latency is acceptable for the hard questions.

Choose something else if

  • Basic retrieval quality has never been measured. Start with RAG system development.
  • Nearly all questions are simple lookups, where this adds cost and latency for nothing.
  • Sub-second latency is a hard requirement on every request.
  • The content itself is contradictory and unowned; planning cannot resolve that.
Questions

Frequently asked questions

Marked up with FAQPage schema so these answers can surface directly in search results and inside AI assistant responses.

What is agentic RAG?

It is retrieval augmented generation where the system decides how to retrieve rather than issuing one search: it decomposes the question, chooses sources, judges whether the evidence is sufficient, searches again if it is not, and verifies its answer against what it found before returning it.

When is agentic RAG worth the extra cost?

For multi-hop, comparison, aggregation, temporal and conditional questions, and anywhere a confident wrong answer is expensive. For simple lookups it is a waste, which is why we route traffic by question type rather than sending everything down the expensive path.

How much slower is it?

Several times, typically seconds rather than under a second, because it performs multiple retrieval rounds and a verification pass. We bound the number of rounds explicitly and report latency per question type so the trade is visible rather than discovered in production.

Does it eliminate hallucination?

No, and nobody should claim that. It reduces it substantially, mainly through the verification pass and by making 'not found in the available sources' an acceptable and frequent output. Residual risk remains and is documented rather than dismissed.

Do we need standard RAG first?

Yes. Agentic retrieval amplifies the quality of the underlying index in both directions: good recall makes plans effective, poor recall makes them expensive and futile. We measure and fix the foundation before adding a planning loop to it.

Is this the right engagement?

Tell us what you are trying to build. If a different service fits better, or if you do not need us at all, we will say so.