--- title: "Agentic Verification: proof your deposit builds | Codekeeper" description: Codekeeper's AI agents rebuild your deposit in a sealed environment and issue a Recoverability Certificate for every passed run. In every Pro plan. canonical_url: https://codekeeper.co/agentic-verification --- # Agentic Verification. Proof your software builds. _In hours, not weeks._ AI agents take your escrow deposit into a sealed lab, work out how it's built, and build it. Every passed run issues a Recoverability Certificate, with the date on it. Included in **Escrow Pro, Resilience Pro, Continuity Pro, and Software Backup Pro**. Up to four runs a year, on supported technology stacks. [Book a demo](https://codekeeper.co/book-a-demo) Get the sample evidence pack * Codekeeper's own AI, off public models * Sealed off from the internet ![An engineer watches a rebuild finish in the verification lab](https://codekeeper.co/hubfs/codekeeper-site/images/scenes/agentic-verification-1200.webp) Payments Core · Run #11 Escrow Pro · Codekeeper AI Verification Lab 1. Pre-flight check_Stack matched_ 2. Seal the environment_Sealed_ 3. Restore the deposit_Restored_ 4. Work out the build_1 private package resolved_ 5. Isolated compile_Compiled from source_ 6. Start and check_Health checks passed_ 7. Write the evidence_4 documents_ Passed · Sep 3, 2026 Recoverability Certificate issued Example run of Agentic Verification for an application called Payments Core, with example values: seven steps from the pre-flight check to the evidence, passed on Sep 3, 2026, with a Recoverability Certificate issued. Trusted by 3 500+ teams in over 150 countries, from regulated enterprises to fast-growing software vendors ![Airbus](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/airbus.svg) ![Bayer](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/bayer.svg) ![European Parliament](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/eu-parliament-dark.svg) ![General Motors](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/general-motors.svg) ![Intuit](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/intuit.svg) ![Nestlé](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/nestle.svg) ![PepsiCo](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/pepsico.svg) ![Pfizer](https://codekeeper.co/hubfs/codekeeper-site/logos/customers/pfizer.svg) What's new ## Rebuild tests used to be a project. _Now they're a button._ A manual build test means weeks of specialist work, engineers to book, and quotes to approve, so it was priced for the largest contracts. Agentic Verification runs in hours, whenever you press run, up to four times a year, included in every Pro plan. Side by side with a typical manual build test Before A typical manual build test Specialists, booked per engagement * _Time_Weeks of specialist work * _Starting a test_Engineers to book, quotes to approve * _Cost_Priced for the largest contracts * _The vendor_Often relies on the vendor's engineers * _Evidence_A report at the end of the engagement Now Agentic Verification AI agents, in the Codekeeper lab Included in Pro * _Time_Hours * _Starting a test_Press run, whenever you choose * _Cost_Up to four runs a year included, on supported technology stacks * _The vendor_No vendor help on a complete deposit * _Evidence_A report for every run, and a certificate for every passed run Need specialists to recover the software and test the functions you nominate? That's an [Exit Exercise](https://codekeeper.co/exit-exercise) . Inside a run ## Press run. _The agents do the rest._ From your deposit to a certificate, with nobody to book. Up to four runs a year, on supported technology stacks, started whenever you choose. 1. 1 ### Pre-flight check The agents read the deposit and match each part to a supported technology stack. 2. 2 ### Seal the environment A clean environment opens in the lab, for this run only. 3. 3 ### Restore the deposit Repositories and documents come back as deposited. 4. 4 ### Work out the build The agents study how it's built and resolve its dependencies, private packages included. 5. 5 ### Isolated compile The software is compiled from source, inside the sealed environment. 6. 6 ### Start and check Services start, and health checks confirm the application runs. 7. ### Write the evidence Rebuild Report, SBOM, and exit workbook. A pass adds the Recoverability Certificate. Illustration of a typical run. The exact steps depend on the technology stack. Not sure your stack is supported? [Take the free technical assessment](https://codekeeper.co/technical-assessment) : tell us how your application is built, and our escrow engineers will recommend what to deposit and which verification level you need. 0:00 / 1:11 **Agentic Verification**Proof it builds, in hours1:11 Starting a run ### Start it whenever you choose. * Start a run whenever you choose: before an audit, after a release, or when the deposit changes. * No engineers to book and no quotes to approve. * Between runs, we compare the deposit with the live repositories and flag what's changed, so you know when to run again. What you get ## Four documents. _One answer you can hand over._ Every passed run adds a dated set to your record, each document answering a question someone will put to you. ![The sample evidence pack for an example run: a Recoverability Certificate, a Rebuild Report, and SBOM and exit workbook excerpts](https://codekeeper.co/hubfs/codekeeper-site/images/agentic-verification/sample-evidence-pack-stack-1875.webp) Example Recoverability Certificate and Rebuild Report for a fictional application, with example values. Testing your day-to-day functions is an [Exit Exercise](https://codekeeper.co/exit-exercise) . * Recoverability Certificate ### Did it build, and when? The application, the result, and the date, on one page you can hand to an auditor or a client. * Rebuild Report ### How did it build? Each step the agents took, what compiled, and anything that was missing. * SBOM ### What's inside it? Every component the build used, direct and transitive, with versions and licenses, in CycloneDX. [More about SBOMs →](https://codekeeper.co/software-bill-of-materials) * Exit workbook ### How would we recover it ourselves? The recovery, step by step, written from the run: environment, deposit, build, configuration, and checks. * Plus a tested isolated compile ### Is it ready to deploy? Every passed run also produces a ready-to-deploy build. It's held with the deposit until a release, when the software user gets it. ### See the evidence before you talk to us. The sample evidence pack holds the Recoverability Certificate and Rebuild Report from one example run, with SBOM and exit workbook excerpts, all with example values. Get the sample evidence pack Who it's for ## Proof for both sides _of the agreement._ The software user and the vendor get the same dated evidence from the same run. ![An IT risk lead walks an external auditor through a printed report at a meeting table](https://codekeeper.co/hubfs/codekeeper-site/images/agentic-verification/who-risk-lead-1200.webp) 01 · Software users ### You rely on the software. Asked by auditors, risk teams, and your board. * Know the software you depend on can be rebuilt * Answer audit and risk reviews with dated evidence * Spot gaps while the vendor can still fix them See the plans that include it → ![A software vendor's engineering lead answers a client's security review on a video call, with the questionnaire on a second screen](https://codekeeper.co/hubfs/codekeeper-site/images/agentic-verification/who-vendor-lead-1200.webp) 02 · Software vendors ### You build the software. Asked in client security reviews and procurement. * Answer client security reviews with a certificate * Show what's in your deposit before a client asks * Get an exit workbook that shows clients their recovery is already planned [Codekeeper for software vendors →](https://codekeeper.co/software-vendors) When a run finds a gap ## Found a gap? _You found it early._ The Rebuild Report names it, the vendor adds it to the deposit, and you run again. **Run #10**Payments Core 1 item flagged * Pre-flight check * Deposit restored * Dependenciesledger-core 4.2, a private package, isn't in the deposit Flagged in the Rebuild Report for the vendor 1. **Sep 1**Vendor notified 2. **Sep 2**Package added to the deposit **Run #11**Payments Core · Sep 3, 2026 Passed * Dependencies resolvedIncluding 1 private package * Isolated compile * Started, health checks passed Recoverability Certificate issued Example values, the same example as in the sample evidence pack. Security ## Sealed. Private. _Our own AI._ Your code stays in Codekeeper's environment. Runs use Codekeeper's own AI, which keeps your code off public models, and each run is sealed off. Codekeeper AI Verification Lab A sealed environment for each run. Inside it: * Your deposit * Codekeeper's AI agents * Codekeeper's own models No connection to * Production systems * Development systems * The open internet * Public AI models ### Own models, own infrastructure. The agents run on Codekeeper's models, in Codekeeper's environment. ### The vendor stays in control. The vendor can add or remove materials at any point, and a run uses only what's there. ### Independently certified. Codekeeper is ISO/IEC 27001:2022 certified. Plans ## Included in _every Pro plan._ Escrow Pro, Resilience Pro, and Continuity Pro, each with up to four runs a year, on supported technology stacks, and the full set of evidence. Choose by how you want to recover. Software Backup Pro includes it too, for the software your own team builds and runs. | Plan | Softwarefrom | SaaSfrom | AIfrom | | --- | --- | --- | --- | | [Escrow Pro](https://codekeeper.co/escrow) Self-Run RecoveryThe deposit is released to you, and your team runs the recovery. | $419 | $599 | $1,019 | | [Resilience Pro](https://codekeeper.co/resilience) Managed RecoveryThe deposit comes to Codekeeper, and Codekeeper's engineers run the recovery. | $599 | $789 | $1,299 | | [Continuity Pro](https://codekeeper.co/continuity) Full ContinuityOn Escrow Pro or Resilience Pro, the live environment is kept paid and switched on for an agreed period, with bills recharged at cost. | $1,569 | $1,799 | $2,219 | | [Software Backup Pro](https://codekeeper.co/software-backup) Your own softwareFor the applications your own team builds and runs, backed up in an immutable vault outside production. | $319billed annually | Not offered | Not offered | One-time setup: $499 per agreement for Escrow Pro and Resilience Pro, $999 for Continuity Pro, and $249 for Software Backup Pro. Escrow, Resilience, and Continuity include the monthly automated check, with a Vault Report and a Vault Certificate, but no rebuilds. [Compare plans](https://codekeeper.co/pricing/compare) [Build a plan →](https://codekeeper.co/pricing/build-a-plan) ## Have the answer ready _before anyone asks._ See a run on one of your own applications, or start with the sample evidence pack. [Book a demo](https://codekeeper.co/book-a-demo) Get the sample evidence pack Frequently asked questions ## Before your first run. What is Agentic Verification? Agentic Verification is the rebuild test included in every Pro plan. Codekeeper's AI agents rebuild your deposit in the Codekeeper AI Verification Lab and document what happened, and a passed run issues a Recoverability Certificate. Does our code go to a public AI model? No, your code doesn't go to a public AI model. The agents run on Codekeeper's own AI and infrastructure, and your code stays in our environment throughout. Does the vendor have to help? The vendor doesn't have to help when the deposit is complete. The agents work from what's deposited, and if something's missing, the run flags it and the vendor adds it. Which technology stacks are supported? We confirm which technology stacks are supported for your application in the demo, so tell us what it's built with. Each run's pre-flight check also matches every part of the deposit to a supported stack before the build starts. How often can we run it? You can run Agentic Verification up to four times a year on each Pro plan, on supported technology stacks. You decide when, so a run can land right before an audit or right after a major release. Is the Recoverability Certificate a compliance certificate? No, the Recoverability Certificate isn't a compliance certificate. It records that the deposit built, and when. You can add it to the evidence for an audit or a review, but whether it meets a particular requirement is for you and your assessor to decide. What if a run doesn't pass? If a run doesn't pass, the Rebuild Report shows how far the build got and what it was missing. Once the vendor adds the missing parts, start a new run. How is this different from an Exit Exercise? Agentic Verification and an Exit Exercise answer different questions. Agentic Verification answers whether the deposit builds. An [Exit Exercise](https://codekeeper.co/exit-exercise) answers whether you could exit and keep working: Codekeeper specialists rebuild the software independently of the vendor, bring back the data, deploy it, and test the business functions you nominate. You can add one to any plan.