AI project recovery: assess, retain and repair with evidence
Recover an AI project by reproducing the intended task and its failures, checking source and operating boundaries, then comparing what to retain, repair or replace. Preserve the evidence behind each component decision. Estimate bounded work, verify transfer and involve the receiving owner before expanding exposure or declaring the recovery complete.

The short version
- Reproduce the blocker. A symptom does not establish its source or solution.
- Decide by component. Retain useful work and compare bounded alternatives.
- Verify the transfer. Access, rights and operating capability need separate evidence.
- Estimate actual work. Separate assessment, repair, replacement and recurring costs.
- Keep expansion conditional. A calendar or cheaper call path cannot settle acceptance.
Recognize a stalled project without guessing the cause
AI project recovery starts by identifying the intended task, the evidence already available and the decision that remains blocked. A favorable demonstration can coexist with weak access, evaluation, integration or operation. Investigate those gaps before adding scope or replacing a model, and contain an active security or operating incident through the appropriate response process.
Consider a SaaS support assistant that drafts internal replies from product documentation and a permitted ticket. The stalled build produces plausible text, but reviewers cannot consistently locate its evidence and its internal draft store sometimes records a draft twice. Recovery should first establish the supported product/source boundary and reproduce those failures. The proposed release remains draft-only; it does not autonomously send replies, close tickets or change accounts.
- Untested exposure: the demonstration has not covered the intended users, source variation, concurrent work or dependency failures.
- Unclear acceptance: people disagree about useful, complete or unacceptable behavior.
- Weak evaluation: important failures cannot be reproduced against a versioned candidate and clear judgment.
- Incomplete economics: the team cannot connect requests, calls, retries and retained review with the cost of an accepted task.
- Moving commitments: scope, dependencies or dates change without an explanation of the evidence and decision.
- Fragile transfer: usable access, rights or operating knowledge depend on an unexplained supplier arrangement.
- Unusable detection: responders lack the evidence or authority needed to investigate a live failure.
Deloitte's technology-value survey discusses expertise and other transformation barriers.4 Such association is context for checking capability, not a diagnosis that every stalled AI build has a skills problem. The AI project failure guide examines underlying causes; a recovery review needs the evidence from this system.
Review ten areas and explain what each gap means
Assess the task, evaluation, sources, implementation, cost, operation, authority, accountability, release and transfer. Use interviews to understand the work and artifacts to verify important claims. Record the consequence, uncertainty, owner and next action for each finding rather than treating a color score as an objective recovery verdict.
Begin with authorized access and a clear investigation boundary. Request the relevant repository, configuration, provider and hosting information, existing evaluations, invoices and suitably limited logs. If access is unavailable, distinguish a contractual restriction, missing permission and a technical recovery problem. Some useful assessment may continue, while a blocked fact remains explicitly unresolved.
| Audit point | Evidence to ask for | Question raised by a gap |
|---|---|---|
| 1. Intended task | Acceptance, baseline and responsible decision | No agreement on useful behavior |
| 2. Evaluation | Cases, versions, judgments and failures | Only a favorable demonstration |
| 3. Sources | Permission, lineage, freshness and coverage | Unclear rights or missing evidence |
| 4. Implementation | Build, dependencies, prompts and configuration | Cannot reproduce the relevant path |
| 5. Cost | Calls, retries, infrastructure and retained work | Unknown unit or incomplete accounting |
| 6. Operation | Request time, failures and load evidence | Only a narrow happy-path run |
| 7. Authority | Roles, tools, limits and denied cases | Consequential access without justification |
| 8. Accountability | Risk decisions and incident responsibility | No one can accept or reduce exposure |
| 9. Release/recovery | Versioned artifacts, observation and restore | Untested partial failure or reconciliation |
| 10. Transfer | Rights, accounts, exports and usable knowledge | Dependence cannot be explained or transferred |

Connect the review areas to reproducible decisions
For the support assistant, retain examples of an unsupported answer, an unavailable source and a duplicate destination write. Reproduce the request path with its relevant versions, then separate source selection, generation, review and integration outcomes. A symptom visible in the final response may originate earlier in the workflow.
- Task and evaluation: define the accepted result and meaningful failure cases. Anthropic describes agent evaluations using outputs, environment outcomes, trials and explicit graders.6 Choose coverage from the task rather than importing a fixed number of cases.
- Data and lifecycle: Google's MLOps guidance connects offline development with deployment and operation.5 Inspect the obligations relevant to this application without requiring a training pipeline it does not own.
- Threat and authority: OWASP identifies disclosure, injection, excessive agency and unbounded consumption among LLM risks.7 Test actual source and tool paths, including denied and repeated operations.
- Accountability: NIST AI RMF treats risk tolerance as contextual.8 Determine who can accept the proposed exposure, limit it and respond when intended behavior is not met.
- Transfer: identify the access, rights, formats and knowledge the receiving owner needs. Account names alone cannot establish legal ownership or operational independence.
Do not let a summary rating hide a consequential gap. An active disclosure or unauthorized action may require containment before an ordinary repair plan. A missing performance observation may instead justify a bounded test. Escalate according to consequence and authority, with appropriate security, legal or business involvement where needed.
The evaluation guide develops task cases and judgments, while governance cases illustrate distinct authority and response questions. Use them to sharpen the local review without assuming a framework reference settles the findings.
Choose what to retain, repair or replace by component
Retain components supported by the required evidence, repair bounded deficiencies and compare replacement where the current approach cannot reasonably meet the task or operating conditions. A mixed outcome is often plausible. Missing information calls for investigation; it does not automatically justify a rewrite of the whole project.
| Component | Keep when | Fix when | Rebuild when | First test |
|---|---|---|---|---|
| Task and value | Useful task and acceptance are supported | Clarify a specific criterion or baseline | Reconsider the task if value is unsupported | Observe the actual user workflow |
| Data | Permitted source coverage meets the task | Repair extraction, access or freshness | Test an alternative when needed sources cannot be used | Trace a representative source record |
| Model/prompt | Relevant cases meet acceptance | Target a demonstrated behavior or context gap | Compare another candidate if evidence warrants | Run equivalent cases and preserve failures |
| Serving | Required behavior fits operating constraints | Repair a measured bottleneck or failure | Prototype an incompatible requirement elsewhere | Exercise load and dependency failures |
| Evaluation | Cases and judgments support decisions | Improve coverage or reproducibility | Build missing evaluation capability | Reproduce an important failed case |
| Authority | Permissions match intended operations | Reduce unjustified access and add checks | Redesign a fundamentally unsafe action path | Test allowed, denied and repeated actions |
| Implementation | Receiving owner can build and maintain | Document and repair bounded opaque areas | Compare replacement with migration obligations | Build and investigate from clean access |
For the support assistant, the existing document importer may be usable while source citation needs repair and destination-write handling needs redesign. Verify each hypothesis. Test the current model with corrected evidence before concluding it is the constraint, and compare alternatives on the same accepted task rather than a favorable new demonstration.
Keep the product question open. If staff do not need generated replies but do need better document lookup, a narrower feature may be the useful recovery. Unusable source rights or unsupported business value can require rescoping or stopping, not simply more infrastructure.
- Compare future paths: retain useful evidence and account for migration, transition and operation. Sunk effort cannot establish which option now meets the need.
- Change one hypothesis clearly: distinguish prompt, retrieval, model and integration changes where feasible, recording concurrent changes that affect interpretation.
- Replace within a boundary: a new component still needs acceptance, source permission and recovery evidence; it is not exempt because the old one failed.
The PoC-to-production guide expands those connected release responsibilities. Preserve the old system's useful task knowledge without copying its unsupported commitments into the replacement scope.
Use a review calendar with conditional checkpoints
A 30-60-90 day example can organize assessment, selected repairs and a supported release or handover. It is a planning calendar, not an expected recovery duration. Make the checkpoints capable of extending, narrowing or stopping work when access, feasibility, operating risk or value remains unresolved.
In this example, the first period establishes the draft-only task, source boundary and reproducible citation/duplicate-write failures. It also handles any active exposure and creates a baseline. Later work targets justified repairs and verifies them before the receiving team accepts a limited operating scope. Discovery may change the calendar.
| Phase | Goal | Main work | Deliverable | Exit gate |
|---|---|---|---|---|
| Days 1 to 30 | Understand and contain | Access, task baseline, gaps and urgent response | Evidence map and bounded options | Continue, investigate, rescope or stop |
| Days 31 to 60 | Verify selected repairs | Targeted implementation, evaluation and recovery | Results against the original question | Accept supported scope or revise |
| Days 61 to 90 | Observe and transfer | Limited release where justified; paired operation | Operating evidence and receiving-owner record | Owner accepts the tested boundary |
Set meaningful checkpoint artifacts: accepted task criteria, a reproduced failure, a tested repair and an operator completing recovery. A deadline alone should not convert missing evidence into approval. Review the current commitment with the people who can accept its business and operating consequences.
- Establish the comparison: preserve actual baseline cases, complete retained effort and the versions tested. A recovery may improve one task while leaving another unsupported.
- Limit exposure: use a staged path appropriate to the consequence, with detection and a capable response. Do not assume every data or external effect can be undone automatically.
- Transfer while learning: involve the receiving owner in the investigation and verification so handover does not begin only after the implementation team leaves.
The AI release checklist helps preserve evidence for the next exposure decision. Reassess when new data, users or actions enter scope; the original pilot cannot stand in for those tests.
Transfer usable access, rights and operating knowledge
A workable handover lets the receiving team build, operate, change and investigate the supported system under the applicable rights and contracts. Inventory code, configuration, data, derived artifacts, accounts, licenses, evaluations and recovery knowledge. Verify the transfer through real tasks rather than assuming every asset must or can be assigned without conditions.
OMB M-25-22 addresses portability, documentation and vendor-lock-in protections in US federal AI acquisition.10 It offers useful procurement context, but its federal scope is not a law governing every private takeover or a guarantee that all third-party models and code transfer. Review the actual agreement and licenses with the responsible people.
- Implementation: identify repositories, build/deployment configuration, prompts, dependencies and release artifacts needed for the supported path.
- Accounts: verify administrators, collaborator access, credential handling and the sequence for transfer or replacement. Preserve evidence needed for incident investigation.
- Data: agree usable formats, source rights, deletion obligations and treatment of derived indexes or outputs. Test an export and import where transfer is required.
- Models and components: identify provider terms, usable weights where applicable and licenses. NIST's Generative AI Profile addresses distinctive risks and management actions involving such dependencies.9
- Evaluation: transfer permitted cases, judgments, configuration history and known limits so the next team can reproduce important findings.
- Operation: provide runbooks and practice build, release, failure investigation and recovery with the receiving owner.
Plan a factual transition with the outgoing supplier
Use the existing contract, access obligations and relevant business/legal advice to arrange the transition. Agree the evidence, people, dates and commercial terms needed for knowledge transfer. Keep requests specific: a missing configuration, an unusable export or an unreproduced failure is easier to resolve than a general accusation that the system does not work.
Coordinate credential changes and data movement so the transition does not destroy needed access or create a new exposure. Record unresolved rights or dependencies and their effect on the plan. A cooperative handover can still need independent verification of the receiving team's capability.
Select recovery help by the problem it can verify
Ask a prospective team to explain its assessment method, the lead's role, relevant permitted evidence and how it will distinguish repair from replacement. Confirm what access it needs, what the first bounded finding will be and who operates the result. A supplier category or claimed project-success percentage cannot establish fit for this inherited system.
Assess your own retained capacity as well. Domain decisions, source permission and acceptance may remain with the buyer even when a partner implements the repair. Use the development partner evaluation guide to compare responsibilities and evidence rather than assuming a change of vendor resolves the underlying constraint.
Estimate recovery from the findings and the supported task
Price assessment and recovery from the actual system boundary, access, uncertainties and work required to verify the result. Separate alternative repair and replacement scopes from optional integration and ongoing operation. Avoid mapping an inherited project to a generic price range before knowing what can be retained and what needs evidence.
For the draft-only support assistant, assume one application, one product documentation set, two user roles and one model-provider path. The assessment budget is 40 hours: 8 for access/inventory, 12 for reproducing task failures, 12 for source and integration inspection and 8 for bounded options. The hourly rate below is a chosen USD 100 for transparent arithmetic, not a supplier quote or market benchmark.
| Work package | Assumed effort and cost | Boundary or dependency |
|---|---|---|
| Assessment | 40 h × USD 100 = USD 4,000 | One app, source set and model-provider path |
| Bounded repair | 160 h × USD 100 = USD 16,000 | Targeted access, evaluation and release work |
| Alternative replacement | 368 h × USD 100 = USD 36,800 | Same limited drafting task; migration included |
| Optional integration validation | 56 h × USD 100 = USD 5,600 | New external draft attachment; internal-store repair separate |
| Ongoing support allowance | 12 h/month × USD 100 = USD 1,200/month | Chosen capacity; usage and availability terms separate |
The repair option's 160 hours budgets 40 for source/citation work, 40 for access and duplicate handling, 50 for regression/recovery and 30 for release and transfer. For the replacement, reuse the assessment’s task criteria, permission map and reproduced failures; its separate 40 hours are not charged again inside this option. Allocate 48 hours to a source importer, 64 to retrieval/citation logic, 48 to the draft/review interface, 32 to role enforcement, 72 to evaluation and correction, 40 to data transition, 40 to release/recovery and 24 to receiving-team transfer: 368 additional hours. The transition assumes at most 100 current documents and 500 internal drafts, stable record identifiers and two role mappings. Include a trial import, record/source reconciliation and a rollback rehearsal; historical ticket migration is excluded.
Optional integration adds one new ticket-system draft attachment path, beyond the existing internal draft store. Allocate 12 hours to the destination contract and authentication, 16 to its adapter, 12 to state/idempotency handling, 8 to denied/timeout/retry tests, 4 to buyer acceptance and 4 to operator handover: 56 hours. Repair already fixes duplicate handling in the internal store; this optional line validates a different external destination and its confirmation/read-back path. It cannot send replies, close tickets or change accounts. Reuse the assessment’s source/role findings but inspect the new destination contract separately. These are chosen task estimates that actual interfaces and failures may change. The monthly allowance reserves chosen support capacity; it does not promise continuous coverage or include every incident. Do not add repair and replacement as if both are required. The separately priced assessment informs either option; its accepted findings are reused, with new implementation and verification allocated above.
Hosting, provider usage, tools, specialist independent review, tax and unpriced internal participation are excluded. Estimate elapsed time separately from hours, using available productive capacity and external dependencies. The AI engagement pricing guide develops scope and contract questions without supplying a transferable quote for this recovery.
Investigate consumption without weakening the accepted task
Trace the actual call path before selecting a cost lever. One request can trigger extraction, retrieval, generation, validation and retries. The illustration holds requests at 100 and varies chosen calls per request; real consumption also depends on model, input/output lengths, cache behavior and unfinished work.
| Path | Assumption | Result |
|---|---|---|
| Four-call path | 100 requests × 4 | 400 calls |
| Five-call path | 100 requests × 5 | 500 calls |
| Two-call path | 100 requests × 2 | 200 calls |
| One-call path | 100 requests × 1 | 100 calls |
- Caching: Anthropic distinguishes write lifetimes and model-specific read pricing.11 Check eligibility, expiry, hit rate and the actual model's rates. Do not assume every reused-looking token is billed at one universal discount.
- Asynchronous work: OpenAI Batch supports eligible work at 50% lower costs with a stated 24-hour turnaround.12 Confirm the deadline and failure/retry handling fit; that pricing difference is not a 50% reduction in total application spend.
- Routing and model choice: compare candidates on the same cases and complete costs, including retained review. Fewer calls or a smaller model can change the result and need verification.
- Limits: test usage controls and their effect when reached. OWASP identifies unbounded consumption as a risk,7 but a token cap alone cannot establish a whole-system budget ceiling or safe continued service.
Keep useful quality, authority and operating evidence beside the cost comparison. The AI cost optimization guide examines those tradeoffs. A favorable provider rate is only one input to the cost of an accepted, supported task.
A recovery decision needs a reproducible task, an accepting owner and evidence that the proposed change addresses the observed failure.
Resourcifi's AI integration team can discuss an inherited assistant using its task evidence, access constraints and known failures. Bring those materials, current usage and the proposed receiving owner to an AI project recovery discussion so the next assessment or repair has a concrete boundary.
AI project recovery questions
Where should AI project recovery begin?
How do you decide whether to repair or rebuild?
Does a 30-60-90 day plan promise recovery in ninety days?
What is needed for a usable vendor handover?
How should recovery cost be estimated?
Can caching or batch processing prove the recovery will save money?
Like this? Get more from Resourcifi in Google Search.
Sources
- deloitte.com, AI and tech investment ROI | Deloitte Insights. Transformation barriers and expertise concerns in a survey.
- docs.cloud.google.com, MLOps: Continuous delivery and automation pipelines in machine learning | Cloud Architecture Center | Google Cloud Documentation. ML lifecycle automation and production-operation boundaries.
- anthropic.com, Demystifying evals for AI agents. Agent evaluation trials, graders and environment outcomes.
- genai.owasp.org, LLMRisks Archive - OWASP Gen AI Security Project. LLM application threats and consumption risk.
- nvlpubs.nist.gov, NIST.AI.100-1.pdf. Contextual AI risk tolerance and accountability.
- nvlpubs.nist.gov, NIST.AI.600-1.pdf. Generative-AI risks and management actions.
- whitehouse.gov, M-25-22-Driving-Efficient-Acquisition-of-Artificial-Intelligence-in-Government.pdf. Federal AI acquisition portability and documentation context.
- platform.claude.com, Prompt caching - Claude Platform Docs. Model-specific cache reads, writes and lifetimes.
- developers.openai.com, Batch API | OpenAI API. Eligible asynchronous batch pricing and turnaround.
Strategy, architecture & ops
Agentic design patterns: choose the right control flow
Compare agentic design patterns by task, evidence, tools and control flow. Test retrieval, routing, agents, cost and reco...
Read guide →
Strategy, architecture & ops
AI cost optimization: measure tasks, compare changes and preserve quality
Plan AI cost optimization from task-level usage, caching, routing and retrieval, with explicit cost assumptions and tests...
Read guide →
Strategy, architecture & ops
AI feature validation: test value before a larger build
Use AI feature validation to compare the task baseline, implementation choices and failure cases. Record correction, pilo...
Read guide →
Strategy, architecture & ops
AI governance failures: cases, controls and assessment
Examine AI governance failures through reported cases and evidence checks for ownership, testing, agent permissions, vend...
Read guide →
Strategy, architecture & ops
AI in production: targets, evidence and operating decisions
Plan AI in production through operating targets, evaluation, bounded release and recovery. Compare build and buy and asse...
Read guide →
Strategy, architecture & ops
AI model deployment challenges: from PoC to production
Resolve AI model deployment challenges through task evaluation, permitted sources, controlled integration and recovery. M...
Read guide →
Agents & RAG
Agentic RAG: step selection, retrieval patterns and evaluation
Understand agentic RAG through routing, corrective retrieval and evaluation, with practical tests for step selection, sou...
Read guide →
Agents & RAG
AI agent development cost: build effort, usage and operating work
Estimate AI agent development cost from scoped build tasks, model calls, tools and upkeep, with a worked support budget a...
Read guide →
Agents & RAG
AI agents for customer service: define actions and verify resolution
Build AI agents for customer service with explicit identity, knowledge, action and handoff checks. Measure verified resol...
Read guide →
