Janis Tirtey
/
[ Method ] Six-Step Plan in 12 Weeks

Six steps. Four agents. Twelve weeks.

The method behind every engagement. Six steps from a manual workflow to a productive digital colleague on your infrastructure. Plain language, no slides, no maturity models.

[ 01 ] Six steps

From process to agent.

Each step has a clear output. You see before we start what lands on the table at the end of the phase, and decide afterwards whether to continue.

5 days
01

Discovery

Map twelve workflows, prioritise top three. Sift WhatsApp groups, email threads, Excel tables. Collect pain points.

OutputWorkflow map
5 days
02

Definition

Fixed-price sketch per phase. DPA template, GDPR briefing for your DPO. Specify test set, define eval metrics.

OutputFixed-price offer
3 weeks
03

Build

Pilot workflow live. Anthropic SDK on your infrastructure. Trust ladder L1 to L4. Test-set eval, logging, monitoring.

OutputLive workflow
2 weeks
04

Validate

Three weeks production eval. Document edge cases, gradually raise trust level, gather error patterns for the runbook.

OutputEval report
8 weeks
05

Scale

Rollout to all prioritised workflows. Per-team training, escalation runbook, cost caps, on-call rotation.

OutputScaled stack
Day X
06

Handover

Handover to your IT. Nobody needs to call me when something breaks. Optional retainer for monthly monitoring.

OutputFull handover
Pre-decision

Should I build custom at all, or will a SaaS tool do?

Honest comparison: 10 axes, decision tree, quadrant. So you do not buy the wrong tool.

Read the comparison
[ 02 ] Four agent archetypes

Bella, Sven, Rita, Klaus.

Four patterns that recur in 80 percent of Mittelstand engagements. Names are placeholders, the patterns are real.

Bella
runs the process

Multi-step processes with branches. Bella decides which sub-agent handles which piece.

typeorchestrator
trustL4
runs/d120
Sven
sorts your inbox

Reads incoming mails, tickets, receipts. Classifies, drafts replies, escalates on edge cases.

typetriage
trustL3 / L4
runs/d412
Rita
reviews contracts and receipts

Checks contracts, receipts, reports for completeness and compliance. Lists anomalies in prioritised form.

typereview
trustL2 / L3
runs/d95
Klaus
keeps reports and data in sync

Recurring ops tasks. Consolidate reports, keep data in sync between systems, trigger-based actions.

typeops
trustL4
runs/d52
[ 03 ] Trust ladder

Four levels from read-only to autonomous agent.

You decide when the agent reaches which level. Read-only first, then suggestion, then auto-action with review, then autonomous. Escalation under uncertainty is always built in.

L1 / Read-only
Observe

Agent reads data, creates reports. No action, no write rights. Usable as a briefing tool for the human.

ExamplesContract briefing, mail summary, data dashboard
L2 / Suggest
Suggest

Agent drafts or recommends. Human validates before each action. Suitable for sensitive outputs.

ExamplesReply draft, contract markup, escalation suggestion
L3 / Act + Review
Act, validate

Agent acts autonomously. Human reviews after the fact daily or weekly. Escalation under uncertainty.

ExamplesMail triage, data sync, standard replies
L4 / Autonomous
Autonomous

Agent acts autonomously, human only spot-checks or reviews on escalation. Maximum leverage, highest eval bar.

ExamplesOrder routing, standard reporting, classification
[ 04 ] Stack

On your infrastructure. EU-resident.

Anthropic SDK directly, no vendor platform in between. You keep the stack, you keep the data, you keep control.

User Interface
internal tooling
Agent Layer
/skills/*.md
Anthropic SDK
claude-sonnet
Tool layer
db, mail, ticket
Your infrastructure
aws, azure, on-prem
  • Model
    Claude Sonnet, Opus, Haiku

    Directly via Anthropic SDK, no vendor in the middle. EU-resident on demand.

  • Runtime
    Your own infrastructure

    AWS Frankfurt, Azure West Europe, or on-prem. Code in your IT's git.

  • Compliance
    GDPR, GoBD, ISO 27001-ready

    DPA signed on day one. Audit logging, cost caps, escalation.

  • Handover
    Runbook + on-call

    Nobody needs to call me when something breaks. Per-team training, escalation docs.

[ 04b ] Stack stages

Three stages, depending on activation energy.

Not every company starts at the same level. Three entry stages, same trust ladder principle, same handover.

Stage 01 · Entry

n8n + OpenAI Node

When you have never built an agent. Low activation energy, low trust build. Good for L1 and L2 use cases with two tools in play.

Stage 02 · Mid

Tasklet.ai or n8n + Claude

When the first pilot runs and the second workflow is up. More control granularity, own eval, MCP bridges to DATEV or SAP.

Stage 03 · Deep

Claude Agent SDK / OpenAI Agents SDK

When you need custom logic, multi-step orchestration and audit trail. Code in your IT git, own eval suite, on-prem option.

[ 05 ] Three guarantees

What you get in writing.

These three promises are in every contract. If I do not keep them, you do not pay.

Fixed price per phase

No day rate, no open end. You know before we start what you get and what it costs. If I overrun, that is my problem.

DPA on day one

EU data residency, GDPR-compliant, GoBD audit logging. Briefing note for your DPO included. Reverse-charge invoicing to DE B2B.

Full handover

Nobody needs to call me when something breaks. Runbook, per-team training, on-call rotation. No consultant lock-in, no follow-on costs.

[ Pilot Promise ]

Before you book: read the pilot promise.

Fixed price. Success criterion in writing. Last instalment only on success. 48-hour cancellation. Code ownership from week one. Solo continuity plan.

Read the full pilot promise
[ First call ]

Which workflow is your first pilot candidate?

30 min first call
6Steps
L4Trust
12wLive
(c) 2026 Janis Tirtey Consulting. Kraków, Poland.GDPR-compliant, EU data residency, DPA per Art. 28.