Construction AI agent · RFI and documents
RFI & Document-Control AI Agent
An RFI answer with design content is design, and design is a licensed act. The agent logs, routes and chases — the responder in responsible charge answers and signs.
- Typical delivery
- 4–6 weeks
- Deployment
- Your stack
- Responder signs
- Routing only
- After launch
- Agent Care
What this agent does
Routes the question; it does not answer it
In
- 01
Log every inbound RFI against the drawing, specification and location it cites.
- 02
Log a repeat against the original thread rather than opening a second one.
Reason
- 03
Route each RFI to the named responder the project responsibility matrix sets.
- 04
Route anything carrying design content to the professional in responsible charge.
- 05
Report ageing, response-time breaches and the RFIs sitting on open delay events.
Decide
- 06
Report every out-of-date file in circulation against the register the CDE holds.
- 07
Route the drafted wording to the responder, who decides what is released.
Out
- 08
Log the question, its routing, every status change and the responder's decision.
- 09
Execute write actions only inside the approval boundaries agreed during implementation.
Product statement
The agent logs and routes; the responder in responsible charge answers — and once the field has built to an answer, the remedy is physical work, not an edit.
Example workflow
One RFI, inbox to response
- 1RFI receivedContractor query, site question, submittal comment or coordination issue
- 2Register entry madeThe drawing, specification, location and revision cited, with the status the CDE holds for each
- 3Routing computedNamed responder, discipline, ageing clock, design-content flag and confidence
- 4Controls appliedResponsibility-matrix checks, design-content and scope tripwires, ageing clocks and confidence threshold
No human action required
Stages 1 to 4 run unaided, and nothing is answered or published at any of them — the agent is logging and routing, and the responder's lane opens at the confidence gate.
Goes to the named responder.
Adds a contracts read first.
Responder review
The RFI is held with the documents it cites, its flags and the confidence.
Answer · Reassign · Send to contracts
Answered — released by the responder
- 6Register and CDE updatedOnly where write access and approval policy allow it
- 7Outcome evaluatedResponse time, reassignments, design-content catches and answers disputed afterwards
Reassignments
Every reassignment made in review is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required
8 items
- Answering an RFI with design content.
- Changing an information container's status code.
- Issuing or distributing a drawing for construction.
- Closing, voiding or merging an RFI.
Automation boundary
Agent acts unaided
- ✓Log, deduplicate and index inbound RFIs against drawings, specs and locations.
- ✓Route to the named responder and chase on the agreed clock.
- ✓Report ageing and response-time breaches.
- ✓Reconcile the register and flag stale files.
Any write happens inside the boundaries agreed at implementation, and never onto a status code.
- Declaring a response a variation, a change, or no change.
- Asserting that deemed acceptance has occurred.
- Writing to or amending golden-thread records.
- Deleting or suppressing a superseded revision or comment.
Example output
One RFI, annotated
Everything the agent logs is attached to the documents the question cites.
Register entry · single RFI
Illustrative example- Package
- Façade subcontract
- Question
- Bracket fixing at the slab edge is not shown for this bay
- Open for
- 6 days
- Routing
- Design content — engineer of record
- Confidence
- 95%
- Status held
- Shared, per the project BEP
As received
Taken from the register and the CDE as it currently stands — nothing on this side is written by the agent.
What was read
- Cited drawing revision
- Specification section
- Responsibility matrix
Why this routing
An answer here would carry a dimension, so it goes to the licensee in responsible charge.
What the score decides
Below the configured threshold the RFI picks up a contracts read before the responder sees it.
Action
AnswerReassignSend to contractsValue
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value lands
Value 01 – 04
Every inbound RFI
From the CDE and the register
Apply the project's own protocol
Status codes and responder duties come from the project's BEP and information protocol, which is what governs here.
Route it to the right desk
Routine logging, deduplication and chasing happen before anyone opens the register.
Send review to the design questions
Design-content and scope-change flags are marked, so the responder's read starts where licensure sits.
Build an evidence trail
The question, its routing and every status change stay on the register.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
CDE and document control
- Aconex
- Autodesk ACC
- Procore
- Newforma
RFI workflow
- Procore
- Newforma
- Trimble Viewpoint For Projects
Model authoring and coordination
- Autodesk Revit
- Navisworks
- Solibri
- Revizto
Agent
RFI & document control
- Reads the register
- Routes the question
- Holds for the responder
Markup and handover
- Bluebeam Revu
- Dalux
- ISO 19650 codes
- project BEP
Observability & evaluation
- OpenTelemetry
- Langfuse
- Supported monitoring/evaluation sources
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the field
Each control wraps the one inside it. What a layer does not catch is named in the failure-mode map below it.
L6 · Outermost — last line of defence
Inward → L1 · closest to the model
- L1 – L2
- Test whether a draft may stand
- L3
- Puts the release in the responder's hands
- L4 – L5
- Keep the register and its status changes legible
- L6
- Drops to routing only when signals degrade
How Nestack evaluates it
Evaluate the RFI workflow — not only the finished response.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the answer the field builds to
- E1Final-output evaluationDid the response stay clear of design content and scope change?
- E2Step-level evaluationDid the agent use the current revision, the matrix and the project protocol?
- E3Tool evaluationDid it read and write the correct RFI and the correct register?
- E4Confidence calibrationDo low-confidence RFIs actually attract more reassignments?
- E5Slice evaluationHow does performance change across specific package types?
- E6Business outcomeHow many responses needed rework, or were disputed once built to?
Floor — the work the field actually builds
Failure modes
Where each failure originates in the agent
Seven failure modes, each shown at the stage where it originates.
Agent lifecycle
Direction of processing →
01 · Retrieval
1 mode
- RQ-01
Superseded revision returned
Sorted by upload time rather than the status the CDE holds.
Stage gathers
RFIs, cited drawings, the register and the CDE status
02 · Reasoning
2 modes
- RQ-02
Scope change called minor
A scope-changing answer passes as a clarification and the work is unpaid.
- RQ-03
Deemed acceptance asserted
Acceptance is claimed without the step the contract requires first.
Stage proposes
Routing, cited documents and confidence
03 · Tool / write
2 modes
- RQ-04
Status code promoted
A shared container is moved to a published code and becomes an issue.
- RQ-05
Ageing RFI auto-closed
A bare acknowledgement closes the item and stops the delay clock.
Stage writes
Only where write access and approval policy allow it
04 · Output
1 mode
- RQ-06
Design drafted as a response
A dimension or code reading is attributed to the responder.
Stage returns
The response the responder signs and the field builds to
05 · Change / Version
1 mode
- RQ-07
Status semantics remapped
A platform update publishes containers under the old label.
Stage tracks
Model, prompt, matrix and CDE configuration
- Sev-1 · a held act performed by the agent
- Sev-2 · a wrong answer reaches the field
- Sev-3 · the register degrades, RFI routes to review
Affected slices
A clean aggregate can sit on one package
Aggregate response quality can look acceptable while a few packages carry nearly all of the releases that never reached a licensed responder. Nestack reports the rate by slice, not only in total.
Slice performance — reported separately, not only in aggregate
Illustrative example| Slice | Failure rate | Lift | Lift vs. threshold | Status |
|---|---|---|---|---|
| Delegated-design packages | 3.2% | 3.6× | Review | |
| Higher-risk buildings | 2.5% | 2.8× | Review | |
| Traditional design-bid-build | 1.6% | 1.8× | Watch | |
| Repeat-typology work | 0.8% | 0.9× | Normal |
Bar: unsigned-release-rate lift vs. an all-response baseline · scale 0–4.0× · tick marks the 2.0× review threshold
2 of 4 slices over threshold
Evidence-linked improvement
A cycle closes on a test, not an answer
Closing means the failure is now a case the next release is measured against, not that someone has written up what happened.
Improvement cycle · five stages
Switchback — the path turns at Improve and returns at Learn
- 01
Detect
Unsigned-release rate rises in a package slice.
- 02
Diagnose
Which step let it out — the routing, the tripwire, the register or the queue?
- 03
Improve
A version stamp and the RFI thread travel with the correction.
- 04
Verify
Release is held until the affected register cases clear.
- 05
Learn
Both the suite and the responsibility matrix carry it from then on.
Learn → Detect
The return edge. The next detection runs against a suite one case longer.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, RFI workflow, evaluation, integration, then production validation and handover.
Workstream
Week 1Week 2Week 3Week 4Week 5Week 6
- 01RFI workflow discovery and boundary definition.Week 1
- 02CDE, RFI and model source assessment.Week 1, Week 2
- 03Responsibility-matrix and status-code mapping.Week 1, Week 2
- 04RFI ingestion, deduplication and indexing.Week 2
- 05Routing logic and design-content tripwires.Week 2, Week 3
- 06Confidence scoring and RFI routing.Week 3
- 07Responder review workflow.Week 3, Week 4
- 08CDE and project-system integration.Week 5
- 09Response-quality regression cases.Week 4, Week 5
- 10Guardrails and release controls.Week 4
- 11Register and status instrumentation.Week 5, Week 6
- 12Deployment, documentation and Agent Care handover.Week 6
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallel
Final scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
| Capability✓ in scope · — not at this tier | PilotOne project, one CDE | ProductionProduction CDE and RFI systems | AdvancedMultiple projects / CDEs |
|---|---|---|---|
| Introduced at Pilot | |||
| Logging and routing on your matrix | ✓ | ✓ | ✓ |
| Responder review | ✓ | ✓ | ✓ |
| Response-quality baseline | ✓ | ✓ | ✓ |
| Introduced at Production | |||
| Reporting by package | — | ✓ | ✓ |
| Review workflow in your systems | — | ✓ | ✓ |
| Approved write-back | — | ✓ | ✓ |
| Analytics feed for design teams | — | ✓ | ✓ |
| Introduced at Advanced | |||
| Multi-project CDE rules | — | — | ✓ |
| Multi-stage responder review | — | — | ✓ |
| High RFI volume | — | — | ✓ |
| Enterprise CDE controls | — | — | ✓ |
| Build price | From $5,000 | From $8,000 | Custom quote |
- Final build price
- Confirmed after discovery based on integrations, workflow complexity, RFI volume, approval controls and deployment requirements.
- Separate from build
- Build pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bring
We build with it
01Your responsibility matrix and named responders
→Routing rules and responder mapping
Week 102Representative RFIs and their responses
→Routing baseline, deduplication and design-content tripwires
Week 203Your BEP and information protocol
→Status-code mapping and automation-boundary definition
Week 104Access to relevant APIs, feeds or exports
→CDE, RFI and model system assessment, then integration setup
Week 205RFIs that turned out to be design questions
→Response-quality cases and failure-mode testing
Week 406Which responses may never leave without a licensed read
→Confidence scoring, RFI routing, guardrails and approval controls
Week 307Named responders to review the routing
→Responder review workflow, then pilot and production validation
Weeks 5–6
Nothing else is required
Deployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Each phase sits on the weeks it really occupies. Week 5 runs evaluation and pilot at the same time.
Phase
W1
W2
W3
W4
W5
W6
- DiscoveryW1
- BuildW2 – W3
- EvaluateW4 – W5
- Pilot & LaunchW5 – W6
Week focus
W1RFI workflow discovery, protocol mapping and the automation boundary
W2Source integration and the routing baseline
W3Tripwires, confidence logic and review controls
W4Evaluation suite, guardrails and failure-mode testing
W5CDE integration, pilot packages and targeted corrections
W6A live RFI cycle answered under the responder, then handover
- Reading the band
- Each bar covers the weeks its work is named in and no others. The week 5 overlap is real, not padding.
- At the end of W6
- Sign-off on the pilot register, then continuous monitoring under Agent Care.
- Duration
- Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Construction AI agent
Build an RFI agent around your responsibility matrix.
Show us your CDE, your matrix and who sits in responsible charge. If your RFIs carry design content, the licensee answers and seals — we map what the agent hands them, and what it never touches.
- Typical delivery
- 4–6 weeks
- Deployment
- Your CDE and RFI stack
- Responder review
- Routing only
- After launch
- Agent Care available
Nestack Agents · RFI and document control
AGT-CN-04 · Agent Care available after launch