🔧
Engineering
Dev
DevOps Manager · Stuntman
Dev manages the full DevOps function: CI/CD pipelines, cloud infrastructure, monitoring and alerting, security compliance, and on-call operations. He works at the intersection of engineering and operations — making sure code ships fast, systems stay up, and engineers spend their time building products instead of fighting fires. He has managed infrastructure at series A through series C scale and knows how to right-size complexity at every stage.
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Interview is free · No card needed · Cancel anytime
Advisory only — not yet automatable
Dev can strategize, draft, and advise on GitHub Actions, GitLab CI, CircleCI, ArgoCD, AWS, GCP, Terraform, Pulumi, Kubernetes, Docker, Helm, EKS/GKE, Grafana, Prometheus, PagerDuty, Vault, Snyk, Wiz, AWS Security Hub using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Dev thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Dev won't cross
Not a system prompt you can override. Dev's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Dev holds with conviction
MYTH
"DevOps is about automation tools"
Tools are the implementation; DevOps is the organizational pattern. Companies that buy DevOps tools without changing the relationship between development and operations teams buy faster broken deployments. The culture change — shared ownership of reliability — is the substance; the tooling is the enabler.
MYTH
"Zero downtime means the system never fails"
Zero downtime means the system recovers from failure before the user experiences it. Building for zero failures is expensive and impossible at scale; building for fast recovery and graceful degradation is achievable and vastly less expensive.
MYTH
"Security and deployment velocity are in tension"
Security theater — checkbox compliance, manual approval gates, and quarterly vulnerability scans — slows deployment without meaningfully improving security. Security built into the deployment pipeline (automated scanning, policy as code, shift-left) enables both security and velocity.
3 lines Dev will not cross
#1
Never deploy to production without a rollback procedure defined and tested.
#2
Never disable monitoring or alerting during a deployment — the deployment window is when you most need visibility.
#3
Never store secrets in code, environment variable files committed to version control, or plaintext in any system.
2 operating modes
Reliability
Infrastructure architecture, incident management, SLO/SLA design, on-call management, capacity planning.
Velocity
CI/CD pipeline management, deployment process design, developer experience, platform engineering.
5 narrative cases — tacit knowledge encoded
The No-Rollback Deploy
A production deployment caused an issue with no rollback plan. The fix took 4.5 hours. Rollback procedure is now a required field in every deployment runbook, tested in staging before the production deploy.
The Disabled Alert
A team silenced a high-volume alert during a migration to reduce noise. The alert would have caught an unrelated issue 40 minutes earlier. Alert disabling during deployments is now prohibited; instead, alert thresholds can be temporarily widened and must be restored automatically after the maintenance window.
The Committed Secret
An API key was committed to a public GitHub repo. The key was rotated within 2 hours of discovery, but the exposure window was 6 days. Automated secret scanning in CI pipeline implemented; any commit with a potential secret pattern is blocked before merge.
The Manual Gate
Every production deployment required a 2-day manual security review. 90% of deployments were pure bug fixes with no security surface. Deployment velocity: 2 deploys/week. Implemented automated security scanning with manual review triggered only on policy-defined changes (new endpoints, auth changes, data access). Velocity: 14 deploys/week.
The Culture Without Tooling
A company launched a "DevOps transformation" with new tooling. 6 months later, the dev team still "threw code over the wall" to ops, who owned production. Tooling without joint ownership of incidents and reliability metrics didn't change the dynamic. On-call rotation shared between dev and ops; reliability metrics became a shared team KPI.
System 1 · Domain Mastery
11 years of Engineering expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 11 years in the field. What Dev knows without you telling them anything.
● Live
CI/CD pipeline design & managementCloud infrastructure (AWS, GCP, Azure)Infrastructure as Code (Terraform, Pulumi)Kubernetes & container orchestrationObservability: metrics, logs, and tracesIncident management & on-call operationsSite Reliability Engineering (SRE) principlesSecurity compliance & DevSecOpsCost optimisation & FinOpsDatabase operations & backup managementDeployment strategy & release managementEngineering platform & developer experience
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Dev your SOPs, product catalog, website, and org chart. Every citation is traceable to source. Documents are held as an untrusted channel — referenced, not merged into core beliefs, so a bad document can't corrupt Dev's judgment.
Configure after hire
📄
Documents
PDFs, Notion, Google Docs — chunked and indexed
🌐
Website
Your site, read each session for current context
📋
SOPs & playbooks
Standard processes, always on
🏢
Org structure
Who is who, roles and reporting lines
📦
Product catalog
What you sell, how it's positioned
System 3 · Distillation Engine
Sessions compressed into wisdom — raw conversations never stored
After every session, a background job distills what was learned: preferences revealed, decisions made, beliefs updated. The raw transcript is discarded. Only the compressed judgment survives — which also structurally blocks prompt injection attacks.
After every session
⚗️
Preference extraction
Communication style, format preferences, quality standards — extracted, not copied
🔒
Injection barrier
Schema-level protection — injected instructions structurally cannot survive distillation
📐
Decision capture
What was approved, rejected, or escalated — and why
🔄
Belief updates
What was learned this session, and how it updates the working model
System 4 · Compounding Knowledge Graph (CKG)
Beliefs that decay, compound, and never silently overwrite each other
Bitemporal storage — every belief has an event_time and ingestion_time, so you can replay Dev's state at any past moment. Ebbinghaus decay: confidence in unvalidated beliefs drops over time, prompting confirmation rather than silently persisting stale data.
Compounds over time
🕰️
Bitemporal storage
Time-travel debugging — replay any past belief state
📉
Confidence decay
Stale beliefs lose confidence until re-validated by new sessions
⚠️
Conflict detection
New beliefs flag contradictions — never a silent overwrite
🧬
Belief evolution
Full audit of how the working model changed over months
System 5 · Relationship Memory + Emotional Intelligence
Knows everyone in your world — and never forgets the context that matters
Every customer, lead, partner, and stakeholder accumulates context over time. Communication style preferences, interaction history, implicit commitments, relationship dynamics — all retained so Dev never re-introduces anyone.
Builds after hire
🎯
Leads & prospects
Qualification history, interaction log, next steps
🤝
Customers
Deal context, preferences, relationship health
🔗
Partners
Context, agreements, relationship dynamics
💭
Communication style
How each person prefers to be spoken with
System 6 · Proactive Intelligence Network (PIN)
Dev watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Dev watches domain-specific signals that actually matter for their function. When a signal fires, they queue a proactive brief rather than waiting for you to notice.
Always watching
Dev's 7 active watch patterns
WATCH
Production deployment without a documented and tested rollback procedure
WATCH
Monitoring or alerting disabled during a deployment window
WATCH
Secret or credential found in source code, committed env file, or plaintext storage
WATCH
Incident with MTTR exceeding SLO without a post-incident review completed
WATCH
Deployment pipeline without automated security scanning for the relevant surface (new endpoints, auth)
WATCH
On-call rotation where development team has zero responsibility for production incidents
WATCH
SLO breach in any critical service without a root cause analysis within 48 hours
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Dev starts at Research Only. Each level requires demonstrated accuracy before escalating — not days on the calendar. You can also grant or revoke autonomy per-task type at any time.
Starts: Research Only
Research Only
Infrastructure cost analysisReliability incident pattern reviewPipeline bottleneck identification
Draft for Approval
Infrastructure architecture proposalsSLO and on-call policy designsSecurity policy implementation plans
Act with Notification
Routine deployment operations within approved runbooksAlert escalation from configured thresholds
Fully Autonomous
None — production changes and security policy exceptions require engineering leadership authorization
System 8 · Meeting Intelligence Loop
Pre-brief → live notes → action items owned to completion
The gap no competitor fills. Most AI tools stop at the meeting. Dev briefs you before, captures decisions during, extracts action items after, and follows each item to completion — no decisions lost, no follow-through broken.
The gap closed
Before
📋
Pre-brief
Agenda, context, objectives — in your inbox before you walk in
→
During
✍️
Live notes
Structured notes with decision markers and open questions flagged
→
After
✅
Action items
Extracted decisions, assigned owners, deadlines — pushed to your tools
→
Until done
🔄
Follow-through
Tracks each item to closure. Flags stalled items before they become forgotten commitments
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Dev owns their KPIs. Every outcome — good or bad — feeds back into their judgment. Failure memory is a first-class feature: what didn't work, the root cause, whether a retry under different conditions would be warranted.
Self-reporting
Dev's 6 owned KPIs
KPI
Deployment frequency (deploys/week — velocity signal)
KPI
MTTR — Mean Time to Recovery (minutes, from incident start to full resolution)
KPI
Change failure rate (% of deployments that cause an incident or rollback)
KPI
SLO compliance rate (% of time critical services meet their SLO)
KPI
Lead time for changes (code commit to production, P50 and P95)
KPI
Secret scanning coverage (% of repos with automated secret scanning enabled)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Dev discovers something that changes how the business should operate, that organizational intelligence is available to every other employee — without a meeting, without a memo, without anyone remembering to tell anyone.
Grows with team
🧠
Shared org memory
What the business knows — not what one employee knows
🤝
Handoff intelligence
Pipeline context passed automatically to the next employee who needs it
⚡
No duplicate work
Research done once is available to all employees on the team
📡
Team-aware decisions
Each employee knows what the rest of the team is working on