Workflow Library
The reusable process designs behind the case studies. Each one names its trigger, its inputs and outputs, which steps a model handles, which steps must stay deterministic, and where a human has to approve before anything changes.
Showing 17 of 17 workflows
17 published workflows
Ordered by where they sit in the operating model, from client intake through to production operation.
- Runtime state: Running in productionPlatforms
Campaign Creation to Delivery
From an operator composing a campaign to messages accepted by receiving providers, through a single mandatory suppression gate and a fail-closed readiness barrier.
Trigger: An operator schedules a campaign, or a scheduled campaign reaches its send time.
- Runtime state: Running in productionInfrastructure
DNS Pre-warming Before Sending
Resolve every recipient domain before the first message leaves, and refuse to start when too few resolve — turning a confusing class of deferral into an immediate, legible failure.
Trigger: A campaign start, before any message is transmitted.
- Runtime state: Running in productionData and Analytics
Lead Discovery and Enrichment Pipeline
Find publicly published business contacts through reproducible searches, validate and classify them, then require a human to review before anything can become a sending list.
Trigger: An operator creates a discovery job, or an enrichment job is queued for a list.
- Runtime state: Running in productionMarketing and Growth
AI Client Intake and Qualification
Acknowledge and qualify an inbound inquiry within minutes at any hour, produce a structured record, and hand to a person before any commitment is made.
Trigger: An inbound inquiry arrives through any channel, at any hour.
- Runtime state: Running in productionMarketing and Growth
AI Content Production
Produce written content from an approved structured brief rather than from a blank page — with editing, fact-checking and a quality gate owned by a person.
Trigger: An approved brief enters production.
- Runtime state: Running in productionMarketing and Growth
AI Visual Creative Production
Generate broadly against the same approved brief, then select and finish by hand — because the expensive part of visual production was always the discarded attempts.
Trigger: An approved brief requires visual assets.
- Runtime state: Partially wiredAI Agents
Agent Finding Collection and Triage
Collect findings from diagnostic agents, collapse duplicates within a time window, and present distinct problems to an operator instead of the same problem stated fifteen ways.
Trigger: A scheduled agent job produces a finding, or an operator opens the review queue.
- Runtime state: Running in productionAI Agents
Incident Diagnosis and Approval
Read-only AI diagnosis during a production incident, with a human approving every action — because the fastest wrong fix is worse than a slower right one.
Trigger: A monitoring alert fires, or an operator reports a symptom.
- Runtime state: Running in productionProduct Delivery
PRD to Production
From a written requirement to a verified production change — context packs, task cards, deterministic commit gates, AI review before push, human approval to deploy.
Trigger: A requirement is written down with acceptance criteria and explicit non-goals.
- Runtime state: Running in productionProduct Delivery
Model Routing Decision
Decide which tier handles a task — including the no-model tier, which is the most valuable rule in the policy.
Trigger: Any task about to be given to an assistant.
- Runtime state: Running in productionInfrastructure
Filter-Sensitive Delivery Routing
Detect when a destination sits behind protective filtering infrastructure and apply the most conservative delivery profile — treating its signals as authoritative rather than as an obstacle.
Trigger: Routing resolution for a destination during campaign delivery.
- Runtime state: Running in productionInfrastructure
Closed-Loop Throughput Tuning
Adjust delivery concurrency from smoothed per-destination outcomes rather than from static configuration — with ceilings a loop can never exceed.
Trigger: Every delivery outcome during an active send.
- Runtime state: Running in productionPlatforms
Delivery Protection Rules
Fourteen rules in four priority bands, evaluated on a fixed tick against live delivery signal, able to throttle or pause without waiting for a person.
Trigger: A fixed evaluation tick while any campaign is sending.
- Runtime state: Partially wiredPlatforms
Automation Workflow Execution
A visual canvas builder whose graphs are executed one node per tick by a separate runner, with wait states, branching and a human approval node.
Trigger: A manual run against a specific recipient, or an RSS feed item.
- Runtime state: Built, dormantPlatforms
Campaign Autopilot Braking
A user-authored rule engine that pauses, stops or alerts on a campaign when a metric crosses a threshold — with a simulate mode, an audit trail, and no scheduler.
Trigger: A human clicking run or simulate against a specific rule.
- Runtime state: Declared, not wiredAI Agents
Agent Workflow Orchestration
Thirty-eight agent workflows declared as YAML capability graphs, each with ordered and parallel steps, an autonomy mode, a token budget and required evidence.
Trigger: A cron schedule, an event on the trigger stream, or a manual run.
- Runtime state: Partially wiredAI Agents
Agent Job Governance Gate
Seven sequential checks between an agent job being scheduled and it being allowed to run, each producing an audited allow, deny or degrade with a machine-readable reason.
Trigger: An agent job is about to execute.