Improve one live engineering workflow
for a team using coding agents.

Rule26 helps engineering leaders in regulated and complex environments make AI-assisted software delivery easier to verify and own: clear human decisions, practical checks, and evidence from real work.

  • One team, one live workflow
  • Named client owners
  • Early evidence from real work
Discuss Your Project See the six-week pilot

The flagship engagement

One team, one live workflow, six weeks. The work happens in the team’s real delivery, not in a separate exercise.

Flagship

Six-Week Agentic Engineering Workflow Pilot

Useful when a team is using coding agents and wants one live engineering workflow to be easier to verify and own, from request and specification through implementation, checks, client-owner review, release, and production follow-up.

  1. Request and specification

    What is asked for, and how it is specified before work starts.

  2. Implementation

    What coding agents and engineers each do, and within what boundaries.

  3. Checks

    Tests and other checks the change must pass, and the evidence they leave.

  4. Client-owner review

    The client’s named owner reviews the change and its evidence, and decides whether to approve it.

  5. Release

    The named owner approves release and accepts any residual risk.

  6. Production follow-up

    What the change did after release: use, rework, and issues.

How the six weeks run

  • Weeks 1–2: map the current workflow, identify decision points and risks, and design practical boundaries, checks, evidence, and named owners.
  • Weeks 3–6: start the pilot in the team’s real work and refine it as release cycles allow.

You get an improved workflow started and refined in real work, with early pilot evidence of what changed.

Six weeks may cover only a few release cycles, so findings are early pilot evidence, not proven ROI or established long-term results. A separately scoped, paid 60-day recheck can assess later outcomes. Throughout, your named owners retain approval, release, and residual-risk acceptance decisions; Rule26 advises and supports the work and does not make those decisions.

Discuss a Pilot

Lower-commitment first step

Accountability and Evidence Map

For teams not yet ready for the pilot. Rule26 helps you document the responsibilities, decision points, checks, and evidence in one engineering workflow.

Ask About the Map

What the map covers

  • The decision points in one engineering workflow
  • Who is responsible at each point
  • The checks and evidence each decision needs
  • A named client owner for each decision

Your named owners retain approval, release, and residual-risk acceptance decisions. The map records who decides and what evidence they need. It is not assurance, and Rule26 does not independently assure a workflow it helped design.

Have one defined question instead? The Initial Technical Review is a limited $500 entry offer: up to 60 minutes working through one defined technical question or proposal with Salma Saad, followed by three prioritized risk and evidence observations and a concise executive follow-up document. It is an initial perspective, not a complete assessment. Discuss the $500 Initial Technical Review. This link schedules a conversation through HubSpot. It does not collect payment or deliver the review itself.

Supporting capabilities

Used within the pilot or scoped separately where they help the workflow work. They support the pilot rather than compete with it.

  • Backlog and customer-conversation preparation. Helping your team prepare for its own customer conversations and turn what it learns into clear, testable backlog items before agents or engineers start work.
  • Measuring feature use and production impact. Defining what to measure after release, such as feature use, rework, and production issues, so the team can see what shipped work actually does.
  • Accountability across the SDLC. Mapping who specifies, implements, checks, reviews, approves, and follows up on a change, from request to production.
  • Engineering workflow design. Designing practical stages, boundaries, and checks for work that involves coding agents, built on how the team already delivers.
  • Developing engineering judgment for agentic software work. Working with engineers and leads on when to rely on agent output, what to verify, and how to review it, drawing on Salma’s experience leading and developing an engineering organization.

For AI built into products

Rule26 also supports AI that ships inside a product, where privacy, security, verification and operational accountability are considered throughout the technical work, not added after delivery.

  • Vendor and architecture review
  • AI evaluation and testing
  • Productization and production readiness
  • Approved AI adoption

We do not determine legal sufficiency, insurance coverage, regulatory compliance, or formal acceptance. Where a legal, clinical, cybersecurity, insurance, or regulatory specialist is needed, we say so and coordinate the technical work alongside them.

Healthcare may include PHI movement, vendor and model boundaries, access controls, and qualified human review.

Legal may include privileged information, citation and source verification, and attorney supervision.

How Rule26 works

  1. UnderstandThe workflow, the stakeholders, and the consequences of failure.
  2. MapDecision points, systems, data movement, vendors, ownership.
  3. ChallengeAssumptions, tool and vendor claims, failure modes, supporting evidence.
  4. DefineBoundaries, checks, client-owner review, and acceptance requirements.
  5. SupportHands-on support alongside internal teams and vendors.
  6. EvidenceA record of what was decided, tested, released, and unresolved.

Why Rule26

  • 30+ years in softwareWorking in software since 1994: roughly 20 years in hands-on development and 10 in engineering and delivery leadership
  • Regulated healthcare leadershipLed a ten-person engineering organization in a HIPAA-regulated environment, 2020–2024
  • Founder advisoryPrior paid work involving technical-team formation, estimation, stack selection, and initial AWS architecture
  • Privacy and AI governanceCIPP/US and AIGP knowledge incorporated into technical decisions
  • Applied AI verificationHands-on product and verification experience through GhostCite
  • Client-side leadershipExperience guiding internal teams, external partners, and complex technical change

Engagements are led by Salma Saad and may include additional specialists when the agreed scope requires them. We sit on the client side of the table and do not resell platforms. When appropriate, we can continue from our findings into a clearly defined delivery workstream, with your named owners still making the approval and release decisions.

GhostCite checks supported legal citations and quotations against public court-record sources without asking a generative model to serve as the verification authority. It does not check healthcare outputs, general enterprise AI, or overall system readiness.

See experience and credentials