Capability 01AI workflow platforms

Turning complex business rules into reliable AI systems.

An enterprise healthcare platform that turns spreadsheets, contract documents and existing schedule records into validated, reviewable and traceable changes for downstream reimbursement systems. I architected it and lead its AI and backend engineering.

Architected
The whole platform: six services, AI orchestration, data backbone and keyless CI/CD
Built
Three of the six FastAPI services myself; the team built the other three
With others
The React interface, built with frontend collaborators and AI-assisted development
Scroll to explore

00System at a glance

Keyless CI/CD across four environments, gated on at least 90% test coverage

Data backbone Cloud Storage · BigQuery · Cloud SQL

Six independently deployable FastAPI services on GKE, with autoscaling

Deterministic workflow engine Registered playbooks · human decision points

A conversational intent layer on Google ADK and Vertex AI, wrapped around deterministic playbooks

Human sign-off enforced before any authoritative write

Internal product names, endpoints, schemas and data are withheld. Every example on this page is synthetic.

Operator interfaceConversation · forms · review · results
Conversational orchestratorIntent · clarification · persistent sessions
Deterministic workflow engineRegistered playbooks · human decision points
Intake and validationRate preparationDocument interpretationDownstream deliveryInvestigation and recovery
Data backbone
Cloud StorageBigQueryCloud SQL
GKE · CI/CD · identity · metrics · centralised logs

01The business problem

A fee schedule is more than a price list.

A healthcare fee schedule describes how covered services are reimbursed: procedures and modifiers, markets, effective and cancellation dates, monetary amounts and the rules that interpret them. Operations teams turn approved business changes into data that downstream reimbursement systems use — so an incorrect or uncertain change affects what providers are paid.

One synthetic schedule, FS-A……holds two kinds of data

Monetary rate record · row-oriented

Explicit amounts

Procedure-level allowed amounts with their modifiers, markets and effective periods. Usually supplied as spreadsheets.

Schedule
FS-A
Market
North
Procedure
PRC-1042
Modifier
26
Setting
Non-facility
Allowed amount
$84.20
Effective
1 Jan 2027
Cancellation
—

Reimbursement configuration · document-derived

Rules that interpret amounts

Percentages, templates, anesthesia factors, lesser-of indicators and professional/technical treatment. Often written in contracts.

Schedule
FS-A
Basis
110% of reference
Lesser-of
Billed charges
Anesthesia factor
52.00
Professional / technical
Split applies
Source
Contract §4.2

Input → requirement → engineering responsibility · hover or tap a row

  1. Spreadsheets

    Arrive in different structures, with codes, modifiers and dates to check

    RequirementConsistent validation before anything reaches downstream systems

    Deterministic intake and validation with row-level issues the user can fix

  2. Contract documents

    Rules are written in prose and tables

    RequirementReliable structured fields, with uncertainty made visible

    Repeatable extraction, AI cross-validation and human review

  3. Existing schedule records

    A schedule can have several effective periods

    RequirementChange exactly the right period and the right rows

    Timeline selection and complete business-row identity

  4. Downstream load

    Long-running, and can partially succeed or time out

    RequirementKnow what succeeded, what failed and what is uncertain

    Row-level correlation, durable status and selective recovery

The aim is not to remove judgment but to place it deliberately: people interpret intent, review what was extracted, approve changes and decide when recovery is safe.

02Requirements → controls

Every control exists for a reason.

Each business requirement became an explicit engineering control. Hover over or tap a requirement to see the control it activates and why it is there.

01

Requirement

Ambiguous intent

Control

Clarification and scenario selection

Requests arrive in plain language and are often incomplete. The intent layer asks for what is missing and resolves a registered scenario — a new schedule, a change to an existing one, or an investigation — before any work begins.

02

Requirement

Invalid business relationships

Control

Deterministic reference checks

Active procedure codes, modifier validity, duplicate code-and-modifier pairs, global versus professional/technical relationships and fee precision are checked by code against reference data. AI may guide the user; it never decides whether a row is valid.

03

Requirement

Precise edits

Control

Complete row identity and constrained fields

An edit is matched on the full business identity of a row, so a neighbour with similar attributes is never changed by mistake. Only approved fields can be filtered, sorted or edited.

FS-A · North · PRC-1042 ·26edited
FS-A · North · PRC-1042 ·TCuntouched
04

Requirement

Business-critical changes

Control

Explicit approval gates

Working data is reviewable and reversible. Nothing reaches the system of record until a person approves it, and a downstream action cannot start before its prerequisites are complete.

05

Requirement

Long-running operations

Control

Persistent workflow state

A shared job context and stage status survive restarts and replica changes, so a long job resumes from what is known instead of starting over.

06

Requirement

Partial delivery

Control

Row-level outcomes and selective recovery

Downstream responses are correlated back to their source rows. Successful rows are preserved; only rows that remain eligible are retried.

07

Requirement

Lost response

Control

Reconcile before retry

A timeout after a state-changing call is an unknown outcome, not a failure. Durable records are checked first, because resending immediately could duplicate work the downstream system already did.

03AI, rules and people

AI handles ambiguity. Code handles consequences.

The architecture deliberately avoids asking a model to perform critical database updates or downstream loads. AI interprets language and documents; deterministic code validates and executes; people correct and approve.

AIinterprets
Intent interpretation

HowGoogle ADK runtime with Vertex AI models

WhyPlain-language requests are ambiguous; the intent layer classifies the scenario and requested action.

Contextual cross-validation

HowModel reasoning over the extracted fields

WhyChecks extracted values against their context and flags low-confidence results for review.

Codevalidates and executes
Document extraction

HowText, table and coordinate reading

WhyLocating expected values must be repeatable for the same document.

Business validation

HowReference and relationship checks

WhyRules must be repeatable and testable — they are never delegated to a model.

Workflow sequencing

HowRegistered playbooks in a deterministic engine

WhyBusiness-critical steps run in a fixed, auditable order and pause at decision points.

Personcorrects and approves
Correction and approval

HowReview workspace

WhyConsequential changes need a person’s decision, and approval is separate from editing.

Phase 1 · agentic edge

Intent and context

An ADK-based intent layer interprets the request, keeps conversation context and resolves the target scenario. Sessions are persisted, so a multi-turn conversation survives a restart or a move between replicas.

Phase 2 · deterministic core

Playbook execution

A deterministic engine advances step by step, calls registered capabilities and waits at explicit human decision points. MCP is used as a connector boundary to downstream tools — not as the business workflow.

Simulated reviewSynthetic contract

One extracted field, end to end

Source context · §4.2“Reimbursement for covered services shall be the lesser of billed charges or 110% of the reference schedule, except where Exhibit B applies.”
  1. CodeExtraction
  2. AICross-check
  3. CodeValidation
  4. PersonReview decision
  5. Approved

Basis 110% of reference · lesser-of billed charges

Lesser-of condition depends on Exhibit B · low confidence

Percentage within policy range ✓ · lesser-of ⚑ needs review

Waiting for a reviewer. Approval stays closed.

Reviewer corrected it: the Exhibit B exception applies. Revalidating…

Corrected by reviewer · revalidated ✓ · ready for approval.

Approved by the reviewer. Only now can the configuration move toward delivery.

A decision is revalidated before approval becomes available — editing never authorises a change on its own.

04Architecture

Explore the system, one responsibility at a time.

Hover over or tap any part of the platform to see its responsibility, the requirement it satisfies, its technology and its safeguards. The connected path lights up while the whole system stays in view.

Experience
Orchestration
Domain capabilities
Data, state and the system of record
Cross-cutting

Guided path Focused direct action

05Data and technology

Files, analytics and operational state are not interchangeable.

Each store has one job. A shared job context travels through all of them, so a support engineer can connect a UI action to a file, a database state, a service log and a downstream result.

Files

Cloud Storage

Source files, corrected outputs, exports and downloadable evidence.

Structured and analytical

BigQuery

Reference data, job staging, analytical views and workflow records.

Operational state

Cloud SQL (MySQL)

Persistent agent sessions and operational tables for explicitly enabled paths.

Shared job context

jobsessionuserstagepurposetimestampsresult location
Orchestrator replicaServing · step 4 of 7
Persisted session · Cloud SQLJob context and conversation intact
Data lifecycle
  1. source
  2. normalised working data
  3. approved records
  4. downstream delivery
  5. reconciliation evidence

A controlled database boundary

Operational persistence was introduced behind compatibility boundaries rather than as a wholesale replacement. Selected preparation and delivery paths can use Cloud SQL through a strict configuration gate, while BigQuery keeps reference data, analytics, broad staging and the flows that have not moved.

  • A request never mixes BigQuery and MySQL operations mid-flow.
  • Database and table identifiers are validated; business values are bound as parameters.
  • Connection settings and credentials come from the environment and secrets, never source code.
  • Business contracts are preserved, so the UI and orchestrator need no per-backend workflows.

Technology, by responsibility · hover or tap a technology

Interface
Services
AI
Integration
Data
Platform
Delivery
Operations

Every technology has one job in the platform.

React · TypeScriptInterface · Operator experience

One journey that renders chat, forms, timelines, grids and results from a shared contract

Python · FastAPIServices · Workflow and domain APIs

Typed, testable services with clear business-named capabilities

DockerServices · Packaging

One versioned image per service

Vertex AIAI · Model access

Managed enterprise model execution for intent understanding and document cross-validation

Google ADKAI · Intent-agent runtime

Standard agent lifecycle, model callbacks and persistent sessions

MCP · RESTIntegration · Downstream connectors

A structured tool boundary without embedding every transport detail in the orchestrator

BigQueryData · Reference, staging, analytics, workflow records

Large structured datasets and SQL-based comparison

Cloud SQL (MySQL)Data · Sessions and enabled operational paths

Transactional access and multi-turn state

Cloud StorageData · Files and evidence

Durable objects with controlled access

GKEPlatform · Service runtime

Health checks, rolling updates, autoscaling and workload isolation

Artifact RegistryPlatform · Container images

Versioned delivery to each environment

GitHub ActionsDelivery · Pipelines

Independent build, test, scan and deploy per service

Workload Identity FederationDelivery · Pipeline access

Keyless, scoped authentication — no stored CI keys

Managed Prometheus · monitoringOperations · Service and queue metrics

Autoscaling signals and runtime visibility

Centralised log searchOperations · Investigation

Correlated events across every service

06Interface contract

One conversation, several workspaces.

The interface sends one consistent interaction envelope — the session, the user action and the available context. The orchestrator replies with a message plus structured interaction data that tells the interface what to render next.

  1. Conversation
  2. Upload
  3. Dynamic form
  4. Timeline selection
  5. Review grid
  6. Approval
  7. Results and recovery

Load the new North market rates for schedule FS-A.

Is this a new schedule, or a change to an existing one?

A change — effective next January.

rates_north_2027.xlsxUploaded · 2 sheets · bound to job J-0001
1 Jan 2025 – 31 Dec 20251 Jan 2026 – 31 Dec 20261 Jan 2027 – open
PRC-104226$84.20✓
PRC-1188QX$41.00⚑ invalid modifier
PRC-2001—$12.75✓

3 rows ready · 0 open issues

Approve and deliver
2 delivered1 needs correctionRetry eligible rows

Synthetic interface mock-up

01 / 07

Conversation

Intent discovery, clarification and status questions

Behind the screenIntent classified as a change to an existing schedule · missing context requested · playbook selected

02 / 07

Upload

The selected playbook requires a spreadsheet or document

Behind the screenSource file stored and bound to the job context · intake stage started

03 / 07

Dynamic form

Structured fields cannot be inferred safely

Behind the screenWorkflow paused at a required-input step · fields defined by the playbook

04 / 07

Timeline selection

An existing schedule has several effective periods

Behind the screenMatching periods retrieved · user’s selection fixes the target period for every edit

05 / 07

Review grid

Validation returns row-level issues the user can correct

Behind the screenValidation results returned · corrections saved and the same checks rerun

06 / 07

Approval

Business-critical changes need an explicit decision

Behind the screenApproval recorded · stage gate opens for downstream delivery

07 / 07

Results and recovery

A delivery, retrigger or investigation produces an outcome

Behind the screenRow-level outcomes persisted · only eligible rows offered for retrigger

Guided orchestration

Most guided interactions return through the orchestrator, so the conversation, the workflow step and the interface state stay synchronised.

Focused direct actions

Some focused panels call a service directly when the action is already unambiguous — such as paging or editing a review grid. Not every click passes through the orchestrator.

I defined the interaction contract and architected the backend behind it. The React interface was built with frontend collaborators and AI-assisted development.

07Delivery and recovery

The last mile is a correlated batch, not a blind write.

Approved records are grouped by business context, sent in bounded batches and correlated back to their source rows. Keep scrolling to see what is known, what is uncertain and what is safe to do next.

  1. Selecteligible or failed rows
  2. Groupschedule and market context
  3. Batchbounded request envelopes
  4. DeliverREST or MCP transport
  5. Correlaterow-level responses
  6. Persiststatus, audit and summary

SyntheticEight rows in two batches

Batch 1
  1. Row 1PRC-1042 · 26✓ Success
  2. Row 2PRC-1042 · TC✓ Success
  3. Row 3PRC-1188 · —✓ Success
  4. Row 4PRC-2001 · —✓ Success
Batch 2
  1. Row 5PRC-2310 · 26✓ Success
  2. Row 6PRC-2310 · TC✕ Failed
  3. Row 7PRC-3105 · —✓ Success
  4. Row 8PRC-4020 · —✓ Success

Explicit rejection

Request rejected with a recorded error. Row 6 rejected: modifier not valid for this procedure. Seven rows keep their durable success.

Evidence established

  1. Transport — a response was received
  2. Service — the service finished its action
  3. Persistence — durable rows were written
  4. Business — the UI and downstream system show the intended outcome

Safe next action

Fix the rejected row and retrigger only that row.

Explicit rejection

Safe action taken

Fix the rejected row and retrigger only that row.

Row 6 corrected and retriggered alone → ✓. Nothing else was resent.

Partial completion

Some rows have durable success and others do not. Batch 2 stopped after its first row. Rows 1–5 are complete and are not resent.

Evidence established

  1. Transport — a response was received
  2. Service — the service finished its action
  3. Persistence — durable rows were written
  4. Business — the UI and downstream system show the intended outcome

Safe next action

Retry only the eligible non-success rows.

Partial completion

Safe action taken

Retry only the eligible non-success rows.

Rows 6–8 retried → ✓. Rows 1–5 were preserved, not repeated.

Timeout or lost response

The outcome is not proven either way. Batch 2 was sent but no response arrived. Rows 5–8 are uncertain — not failed.

Evidence established

  1. Transport — a response was received
  2. Service — the service finished its action
  3. Persistence — durable rows were written
  4. Business — the UI and downstream system show the intended outcome

Safe next action

Reconcile against durable records before any retry.

Timeout or lost response

Safe action taken

Reconcile against durable records before any retry.

Reconciliation found rows 5–7 already applied → marked ✓ without resending. Row 8 was not applied → eligible for a retry.

Completed with evidence

Source, audit and workflow state agree. Every row has a correlated success, durable status and a matching downstream outcome.

Evidence established

  1. Transport — a response was received
  2. Service — the service finished its action
  3. Persistence — durable rows were written
  4. Business — the UI and downstream system show the intended outcome

Safe next action

Present the final result to the user.

Four kinds of evidence

A successful HTTP response proves transport. A healthy service proves it completed its own action. A durable write proves persistence. Only the interface and the downstream system agreeing proves the business outcome — final status comes from durable workflow evidence, never from a status code.

Recovery reuses work

Document interpretation persists its stage output, so a resumed job reuses it instead of repeating expensive extraction. Termination-before-add flows resume from durable stage state.

08Production engineering

From reviewed change to verified service.

Six independently deployable services share one delivery pattern across four environments, with the same controls everywhere.

  1. 01Reviewed changetargets the right delivery branch
  2. 02Tests and quality checksautomated tests and code-quality scanning
  3. 03Versioned containerone image per service
  4. 04Artifact publicationapproved images stored in registries
  5. 05Environment deploymentenvironment-specific GKE configuration
  6. 06Operational verificationhealth, rollout, metrics and business evidence
01

Independent service delivery

Separate pipelines reduce coupling; common controls keep consistency.

02

Environment-specific configuration

Development, test, stage and production use separate namespaces and settings.

03

Keyless access

Pipelines authenticate through Workload Identity Federation — no stored CI keys.

04

Runtime secrets

Injected at runtime, never kept in source or deployment text.

05

Least privilege

Environment-specific service accounts with scoped cloud permissions.

06

Health probes

Readiness and liveness checks protect traffic and enable self-healing.

07

Scaling signals

Request and queue metrics drive replica changes from observed demand.

08

Correlated, bounded logs

Job, session, service and correlation context; allow-listed identifiers only — no request bodies or credentials.

09

Business completion evidence

A healthy pod confirms delivery readiness; it does not prove the rate change happened.

Quality gate as stated in the pipeline: at least 90% test coverage, with static analysis, before a service can be packaged. This is a stated gate, not a measured business result.

09My contribution

What I did, and what the system does.

Personal contribution and documented platform capability are kept separate. Contribution statements come from my own record of the role; capabilities come from the platform’s architecture documentation.

My contribution

  1. Architected the end-to-end platform and led its AI and backend engineering.
  2. Designed all six independent FastAPI services on GKE with horizontal pod autoscaling; built three of them myself, and the team built the other three.
  3. Designed the use of Vertex AI for PDF extraction, confidence signals and natural-language intent routing through a conversational orchestrator.
  4. Designed the BigQuery staging and audit layer and Cloud Storage file handling, with a human sign-off gate before any authoritative write.
  5. Designed keyless CI/CD with GitHub Actions and Workload Identity Federation, static analysis and coverage gates across four GKE environments.
  6. Defined the interaction contract the React interface renders from; the interface itself was built with collaborators and AI-assisted development.

Documented platform capabilities

  1. Deterministic intake validation with row-level issues and revalidation.
  2. Separate handling of monetary records and document-derived configuration.
  3. Conversational intent handling around deterministic playbooks.
  4. Bounded, correlated downstream delivery with selective recovery.
  5. Investigation views with workflow status, row evidence and stable error categories.
  6. Independent services with shared identifiers across one business journey.

No business metrics are claimed: the platform’s value is described qualitatively — more consistent rate quality, fewer manual handoffs, faster issue resolution and safer recovery.

00Overview
  1. 00Overview
  2. 01The business problem
  3. 02Requirements → controls
  4. 03AI, rules and people
  5. 04Architecture
  6. 05Data and technology
  7. 06Interface contract
  8. 07Delivery and recovery
  9. 08Production engineering
  10. 09My contribution

Have a workflow that needs clearer intelligence?

Let’s talk about the problem, the constraints and where AI can help.

Let's talk

Or see the breadth of my work