⚔ SEASON · JUN – AUG 2026

Portcast AI — Mission Dashboard

AI Agents & ETA Models · party: Andrew & Pitch · sources: Notion roadmaps + live ClickUp
Last synced
10 Jun 2026
CHAPTER 1 · JUNE — ship & hardenCHAPTER 2 · JULY — teams buildCHAPTER 3 · AUGUST — scale & measure
Victory conditions why we're on this quest
🤖 AI AGENTS
Make the whole company faster — without DS in the loop

Reclaim hundreds of human hours every month and pass the empowerment test: teams build and run their own agents. Hours must be measured (runs × time saved), not estimated — that's what makes the program credible to leadership.

LVL 2 · 180 h (July) 🏆 LVL 3 · 250 h (Aug) ⚡ ~135 h/mo

XP = verified productive hours/month from the agents catalog. Currently ~75% of the July level-up.

🚢 ETA MODELS
Make PETA decisively beat carrier ETA where customers feel it

Customers judge us on 0–7 days-ahead accuracy. This is the quarter the stack — new model heads, carrier-anchored rules, container-level trust — beats production by ≥5 pp weighted-OTPA on T≤7d, sustained 14 days.

🏆 VICTORY · +5.0 pp +3.63 pp

Rules deployment already banked +3.63 pp (74.85 vs carrier 71.21). Transit Time, Port Stay & meta-models carry the rest.

🎒 Inventory live & earning today
🧠ETA-to-port model v2In prod since ~May 25 · +2–3% over old model in A/B
📏pred_clip_to_carrier (δ=0.75d)Winning rule live · +3.63 pp weighted-OTPA
🤖Code Review AgentEvery portcast-api MR · ~40 h/mo · ~$6/day
🔎Company Research bots ×2slack-er (~30s) + researcher (~8min) · merging in J3
📄Proposal GeneratorIn use by Sales · RFI/RFP extension queued (Y3)
📊Portcast JuniorPostHog metrics on call in Slack
🧮AI Analyst (beta)kpi_dashboard · grows into Self-Serve KPI Analyst (A1)
🛠️Prototypes MCPSelf-serve dashboards on Cloud Run · <$10/mo
👥Claude Team pilot10 users across teams · onboarding sessions running
🚧ML GatewayA/B router mid-build — single-config (ETA J3)
🧙 Party
🏆 Achievements unlocked this season & the run-up
⚠️ Threats & pending choices

⚠️ Active threats

  • 🧍Andrew is the bottleneck — every team agent queues behind one person. Counter: J5 co-build rule — DS enables, teams build.
  • 🔇Code-review noise erodes trust in all agents. Counter: J1 first in line, 2 quiet weeks before anything new ships.
  • 🔑API access stalls July builds (GSC, Ads, Clay, financials). Counter: request credentials in June.
  • ML Gateway slip blocks Transit Time A/B + rules iteration. Counter: manual-edit fallback for the single A/B.
  • 📉Customer escalation on 0–7d accuracy before August. Counter: J1+J2 land the biggest 0–7d lift fastest; weekly readouts.

🔮 Pending choices

  • 🎯Q2/Q3 numeric KPI targets — agents (J6, Nidhi) and ETA (J5, Urvesh/Pitch) have final say.
  • 🛠️Agent Builder platform — Claude projects/skills vs Prototypes MCP vs dedicated builder. Decided by what teams actually use in J5.
  • 🚨Freight-audit alerts — alert-only vs auto-refresh (Pitch/SJ sign-off).
  • Port Stay: model vs rule — answered by ETA J4 this month.
  • 🔁ETA Monitor ownership — Agents A4 vs ETA roadmap; decide before anyone builds it twice.
Cleared In play Decision pending Needs sign-off Locked — unlocks in its chapter · click a node for quest details
Live from ClickUp on 10 Jun 2026 · green chips link actions to their quest · auto-synced daily at 09:00.