BKS open-bridge · live demo

What a real session looks like

Four flows from the team that builds BKS open-bridge — replayed from BKS-Lab's own instance. Branding and work are real; client names are kept generic. The formats are exactly what a live session prints: the morning greeting, the briefing dashboard, an incident handed to a specialist, and first-run onboarding.

bks · your-bridge

Click the terminal to skip ahead Klick ins Terminal, um vorzuspulen

① Morning — session start

$ cd ~/Developer/bks/your-bridge
 ██████╗ ██╗  ██╗███████╗
 ██╔══██╗██║ ██╔╝██╔════╝
 ██████╔╝█████╔╝ ███████╗
 ██╔══██╗██╔═██╗ ╚════██║
 ██████╔╝██║  ██╗███████║
 ╚═════╝ ╚═╝  ╚═╝╚══════╝  lab
⚡ Good morning, Alex.   🔥 5d   🔔 2
▸ BKS-Lab · your-bridge · user/alex
  your-bridge  user/alex  ↑3 ±6
  ⟳ docs(BKS open-bridge): launch strategy + live demo  (1h ago)
  ◆ 11:00  Weekly · BKS-Lab · 45m
  ◆ 14:00  Launch review · BKS open-bridge live demo · 60m
🔴 2 waiting for your review     ⚠ WIP 5/5
┌─ Doing — BKS-Lab ─────────────────────────────┐
│  ● open-bridge-launch  distribution + live demo  │
│  ● bridge-deck         calendar timeline view     │
│  ● bks-news            weekly briefing automation  │
│  +2 more                                      │
└───────────────────────────────────────────────┘
$ claude
<bridge-phase0>
  state=NORMAL · branch=user/alex · config=yes
  3 CORE commits ahead — offer `git merge development`
</bridge-phase0>
> good morning
Morning. Three things since last night:
1. 02:14 — CI went red on BKS open-bridge main: the release publish step
   flaked. Same failure you fixed Tuesday — that fix never reached main.
2. Pages deploys from main, so the live demo hasn't rebuilt since 02:14 —
   and your 14:00 launch review walks exactly that page.
3. PR #61 (bridge-deck) hits day 4 today — your own three-day review
   rule fired yesterday.
Suggest: merge the retry fix first — ~15 min, and Pages rebuilds well
before 14:00. Demo prep second, #61 review after. Want the diff summary?
> what did I fix on tuesday?
One row from work/log.md — Tue 24.06:
  | 14:32 | 🔧 | BKS open-bridge | release publish flaked 3× — pinned retry backoff in release.yml. Config, not code. |
Same root cause, red on main since 02:14 — the pin never left
fix/release-retry. One merge and tonight's 02:14 run is green again.

② /briefing — the daily dashboard

> /briefing
╭──────────────────────────────────────────────────────────╮
│  Week 26 · Tue 24 Jun · 09:02   │   Doing: 5   │  ⚠ 2   │
│  Focus: ship the BKS open-bridge launch demo → open the repo  │
╰──────────────────────────────────────────────────────────╯
── ⚠ Warnings ──────────────────────────────────────────────
  🟡 WIP 5/5 — at cap; close or reclassify before new work
  🟡 Tailscale node-key expires in 18 days
── Focus today ─────────────────────────────────────────────
  💻 open-bridge-launch  distribution + live demo     🟢 doing
  🔧 bridge-deck         calendar timeline view        🟡 doing
  📝 bks-news            weekly briefing automation      🟢 doing
── GitHub (BKS-Lab) ────────────────────────────────────────
  Agents & MCPs #20    4 open · 1 in review
  BKS Operations #25   3 open
── Open PRs (2 human · 1 bot) ──────────────────────────────
  #61  calendar timeline      bridge-deck    ↑ sam     1d
  #18  launch demo            BKS open-bridge    ↑ alex  3h
── Activity (7 days) ───────────────────────────────────────
  44 commits — BKS open-bridge 24 · bridge-deck 13 · bks-news 7
── Calendar today ──────────────────────────────────────────
  ◆ 11:00  Weekly · BKS-Lab · 45m
── Next steps ──────────────────────────────────────────────
  [ ] merge development (3 commits ahead)
  [ ] review PR #61 (bridge-deck) → then it can land
  [ ] renew the Tailscale node-key before it expires

③ Operator — find the bug, TDD the fix, ship

> inbound invoices aren't booking — what happened?
Loading the e-invoicing ops playbook. Dispatching the log-analyst against
the last 3h of fn-invoicing-in-prd logs — read-only, isolated.
  ◐ Task · subagent_type=log-analyst · running …
◇ log-analyst → returned
  Summary      NEW BLOCKER — inbound parse fails in prod since 08:31 UTC; docs stuck in retry
  Scope        last 3h · fn-invoicing-in-prd · 1,120 hits
  Clusters     🔴 parse_error @ map_invoice   54×  08:31→now  NEW
  Correlation  doc_8842 — received OK · parse FAIL @ map_invoice · never booked
  Root cause   payment_means code "59" (SEPA DD) missing from the enum → KeyError aborts the pipeline
That's a code bug in invoicing-service, not the operator. Fixing it test-first.
▸ red  — a test that reproduces doc_8842
  + tests/test_payment_means.py::test_sepa_dd_59
  ▸ pytest -k payment_means
  ✗ 1 failed — KeyError: '59'   ← reproduced
▸ green  — minimal fix
  ~ invoicing-service/mapping.py · payment_means via .get(code, OTHER)
  ▸ pytest · ruff · mypy
  ✓ 214 passed · ruff ✓ · mypy ✓ · coverage 100%
▸ ship
  ✓ commit a3f1c9 · branch fix/payment-means-59 · pushed · PR #87
  ✓ deploy uat → fn-invoicing-in-uat · health ok
  ✓ replayed doc_8842 on UAT → booked
Done: off-spec SEPA-DD code "59" hit an enum with no fallback → KeyError, so every
inbound aborted. Test-first fix red→green, full suite + lint + types pass,
shipped to UAT and replayed doc_8842 — it books cleanly now.
Prod deploy + PR #87 merge are your call. Ship it? [y/n]

④ First run — onboarding

> hi
Hi — I'm ELOPe, the AI running this bridge: your command hub for
agents, repos and standing orders — and I remember every session.
Fresh clone, nothing wired up yet — a 5-minute, reversible fix. I'll:
  1. spin up your user/alex branch (keeps your data out of CORE)
  2. scan your projects folder and map the BKS-Lab ecosystem
  3. pick a theme and wire up your first agents
[y] Let's go   [t] Tell me more   [n] Not now
> y
Great — about 5 minutes.  [A] Identity
  Name      → detected "Alex" from git config. Keep it? [y/edit]
  GitHub    → bks-lab   ·   Projects → ~/Developer/bks
  ✓ created + checked out branch user/alex
  [B] May I look at your setup? (names + structure only, never content)
  ✓ developer   repos across two org folders
  ✓ homebrew    gh, az, rclone, restic, tailscale, pandoc
  ✓ azure-cli   logged in · 1 subscription
  ✓ tailscale   4 devices: mac-mini, macbook-pro, +2
  [C] Based on what I found:
  ① rclone + restic detected → enable backup topology? [y/m/l]
     ✓ infra/backups/topology.yaml scaffolded · backup skill on
  ② tailscale (4 devices) → scaffold infra/remotes/? [y/m/l]
     ✓ infra/remotes/ scaffolded · 4 machines registered
✓ Onboarding complete — your bridge is live. See you tomorrow, Alex.

The live instance of BKS-Lab — the team behind BKS open-bridge. Branding, repos and stack are real, though chapter ④ shows an earlier onboarding revision (see note above); client names are kept generic and there is no customer data, no secrets, no PII. Formats mirror the live briefing, session-start, coordinator/sub-agent and bridge-onboard flows.

Liked what you saw? Run it yourself in a ready-made workspace — 2 minutes, nothing to configure. Gefällt dir, was du siehst? Probier es selbst in einem fertigen Workspace aus — 2 Minuten, nichts zu konfigurieren.

Try it in 2 minutes In 2 Minuten ausprobieren What people run on it Was darauf läuft