Skip to content
Foundations

LLM workflow (chain, route, parallelise)

Deterministic steps with a model inside each. The right default.

Use it when

The process has known steps and the model is needed for one or two of them: classify, extract, draft, summarise. Most business automation belongs here, not in a free-running agent.

Structure

The parts, top to bottom

hover a part to see its job

across every level

Hover or tap any part to see what it does. The light shows the order a request moves through.

Flow

What happens, in order

  1. 1Input event
  2. 2Pre-process & validate
  3. 3LLM step with schema
  4. 4Rule-based checks
  5. 5Next LLM step or branch
  6. 6Write result & trace
Tools

What we typically build it with

Python / TypeScriptPydantic / ZodTemporal or queuesOpenAI / Claude / GeminiPromptfoo

Trade-offs

Less flexible than an agent, far easier to test, cheaper to run, predictable latency. Reach for agents only when the path cannot be known in advance.

What we solve

Problems this architecture solves

Generic problem statements with the flow and the outcomes the industry has documented.

Document intelligence pipeline

Documents keyed in by hand

Invoices, KYC files, claims and contracts arrive as PDFs and photos. People retype them, errors slip through, and the backlog grows every month-end.

How the system works

  1. Ingest PDF / image / email
  2. Classify document type
  3. Extract to a schema
  4. Validate & score confidence
  5. Auto-post or route to review
Multimodal LLMStructured outputsReducto / LlamaParseReview queueERP / LOS integration

Outcome: Documented deployments classify documents in under a second, turn day-long claims backlogs into minutes, and reach 85% no-touch invoice processing within six months with a seven-month payback. DXC with Claude; Vic.ai

Architecture
Orchestrated multi-agent workflow

Swivel-chair work across systems

Onboarding, reconciliation, procurement and approvals require people to read one system and type into another, with rules that live in someone's head.

How the system works

  1. Trigger (email, form, event)
  2. Orchestrator plans steps
  3. Worker agents read & decide
  4. Confirm risky actions
  5. Update systems & log
LangGraph / Agents SDKMCP tool serversCRM / ERP APIsHuman checkpointsTraces & replay

Outcome: CRM-native agents at a regulated vendor deflected 72% of support cases to self-service and saved 7.5 hours per case handled with AI assistance. Smarsh on Salesforce Agentforce

Architecture

Let's build intelligent systems that drive growth

Tachyon is the engineering partner for teams that need AI in production, not in a deck. Start with a free 60-minute discovery call.

Contact

Tell us the problem, we will map it to the architecture

Every great partnership begins with a conversation. Whether you are exploring possibilities or ready to scale, tell us what you are actually trying to build.

Prefer to talk?

Pick a 60-minute slot. No pitch, just an engineer with honest answers.

Book a call

NDA available on request. We reply within one business day.