Projects.

Krnali Labs is where I explore ideas around safe AI enablement and digital trust, through experiments, prototypes and writing.

It’s a place to build, test assumptions and share what I’m learning. If you’re working on similar questions, I’d be glad to compare ideas or try something together.

Projects

Questions we’re exploring.

Skills Factory defines a repeatable job. Sigil bounds the authority to act. VE preserves evidence that others can check. Verifiable credentials carry claims between issuers, holders and relying parties, while Ops helps interpret what is happening in a running environment. Each has a distinct role and stage of development.

Skills Factory

Build and review agent skills

Downloadable builder preview

Turn a useful method into a reusable skill.

Skills Factory is our work on designing, testing and maintaining specialised agent skills. Security Skills Architect is the downloadable builder preview: it defines a skill's inputs, evidence, permissions, checks and failure behaviour, then helps generate application-specific defence skills.

The emerging-vulnerability workflow connects deployed dependency evidence with fresh advisories and code-path review. Its recurring execution needs separately configured collectors and a scheduler. The PHP Composer review skill remains a separate review candidate. Public licensing, native host acceptance and broader operational validation remain open.

krnali Sigil

Scoped authority for agents and CI

In development · SAR / Sigil

Give approved work the authority it needs.

Previously presented here as Secure Agent Runtime (SAR), Sigil gives agents and CI workflows scoped authority for approved work. It keeps the authority decision and credential lifecycle separate from the agent's proposal.

The current foundation includes policy decisions, sessions, scoped credentials and connector workflows. A skill describes the task; it cannot grant itself authority. Customer-enforced delegation and a broader bounded-write executor have their own implementation and acceptance work; the name change does not make those guarantees complete.

Krnali VE

Verifiable Evidence

In development

Leave evidence that can be checked.

Krnali Verifiable Evidence (VE) is our SCITT implementation for verifiable credential workflows and AI agent transparency. It records signed statements in a transparency log and returns cryptographic receipts that can be checked independently.

Development integrations retain selected credential issuance and verification events, agent outcomes and authority decisions. Teams can export the source observations and verify the evidence offline. A receipt establishes that a signed statement was recorded under its trust context; the underlying claim still needs supporting evidence.

Verifiable Credentials

Claims, holders and relying parties

Lab and proof of concept

Make a credential useful in a real decision.

Our credential work covers design, issuance and verification: who makes a claim, who holds it, what they choose to present and why another party should accept it. Credential Lab is our development environment for exploring those workflows.

The EUDI messaging proof of concept brings wallet presentation into a conversation through a single-use verification link. Issuer trust, consent, status and acceptance policy remain explicit. Credential proofs and VE receipts serve different purposes, and neither replaces the relying party's decision. This is lab and proof-of-concept work, with broader acceptance still pending.

krnali Ops

Private preview

Start with what the system can show.

krnali Ops turns Kubernetes observations into findings, baselines and operational context. The observer stays read-only, inside the customer's environment.

Supported remediation has a separate actuator and an explicit approval boundary. The current action raises a Deployment's memory limit, with checks, verification and rollback. A person can grant revocable permission for a recurring, previously verified fix. The application-defence pilot's proposed Ops handoff remains integration work.

Consulting services

Ways to work together.

Alongside the lab projects, I’m open to helping teams think through a specific question, test an idea or develop a proof of concept. These are some of the areas where my experience may be useful.

AI adoption

Find the work where AI can help.

We help organisations identify useful AI applications, assess readiness and turn a broad ambition into a practical adoption plan. The starting point is the work people do, the information they use and the decisions they remain responsible for.

  • Use-case discovery and prioritisation
  • Readiness and workflow assessment
  • Pilot planning, success measures and team enablement

AI workflow integration

Connect AI to the way the business runs.

We design and build AI-assisted workflows around existing systems, data and people. That includes the integration itself and the boundaries around it: what an agent can access, when a person must approve, and how to recover when a step fails.

  • Workflow and integration design
  • Agent, tool and business-system connections
  • Human approvals, evaluation and exception handling

Secure AI operations

Make the operating boundary explicit.

We help teams plan how AI will run, what it can change and how its behaviour will be observed. Identity, credentials, action permissions and operational evidence need to remain clear as experiments become working services.

  • Deployment and access-boundary reviews
  • Monitoring, evidence and incident workflows
  • Controlled changes, verification and rollback planning

EUDI use case development

Turn a wallet capability into a useful process.

We work with organisations to explore where European Digital Identity wallets and verifiable credentials can support a real business decision. We develop the use case, map the trust relationships and build prototypes that make the assumptions testable.

  • Remote verification and credential use-case discovery
  • Holder journeys, consent and relying-party requirements
  • Proofs of concept, integration design and acceptance testing
See our messaging proof of concept ↗

AI policy and governance

Put the rules where the work happens.

We help develop AI policies and governance that teams can apply in daily work. That means named owners, clear decision rights and review processes, with technical controls and evidence that support the policy.

  • AI use policies and accountability models
  • Approval, escalation and exception processes
  • Evidence requirements and ongoing review
Start a conversation ↗

From agents to people

Trust crosses the boundary
of a single system.

Our EUDI messaging proof of concept explores remote identity verification inside a conversation, with the person choosing what to share from their wallet.

Exploring similar questions?

If you’re building something, testing an idea or working through a question around AI and digital trust, I’d be glad to compare notes. There may be something useful we can explore together.

Talk to us