Chatbot (BOT Squad) — Program Roadmap
Delivery / Program Management — team-level rollup across the team's initiatives.
Portfolio
| Initiative | Target quarter | Health | DRI | Implementors | QA | Timeline |
|---|---|---|---|---|---|---|
| Autonomous AI Agent | 2026-Q3 | At Risk | Dimas Fauzi Hidayat | farras.herdicho, samudra.linggar | tito.amanda | timeline |
| AI Agent Knowledge | 2026-Q3 | — | Dimas Fauzi Hidayat | eko.aprianto, samudra.linggar | tito.amanda, izzul | timeline |
| AI Agent Testing | 2026-Q3 | — | Dimas Fauzi Hidayat | farras.herdicho, baghiz.firdausa, eko.aprianto, samudra.linggar | tito.amanda, izzul | timeline |
| Bot-vs-Human Traffic Split (A/B) | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | timeline |
| Mekari Action (AI Agent) | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | timeline |
| Native Integration (AI Agent) | 2026-Q3 | — | Dimas Fauzi Hidayat | agus.suparman, baghiz.firdausa | tito.amanda, izzul | timeline |
| Qontak Action (AI Agent) | 2026-Q3 | — | Dimas Fauzi Hidayat | eko.aprianto, agus.suparman, baghiz.firdausa | — | timeline |
| Unified Agent Quality Scorecard | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | timeline |
| AI Agent Idle Action | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | — |
| AI Agent Monitoring | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | — |
| Multi-WABA Impact | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | — |
| AI Agent Impact Report | 2026-Q3 | — | Dimas Fauzi Hidayat | agus.suparman, baghiz.firdausa | tito.amanda, izzul | — |
| Meta Business Agent Integration | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | — |
| AI Spam Gatekeeper | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | — |
| Automation Flow Builder | 2026-Q3 | — | Dimas Fauzi Hidayat | — | — | — |
| AI Agent Memory | 2026-Q4 | — | Dimas Fauzi Hidayat | — | — | — |
| Branch Bot Response — Customer/Contact Field | 2026-Q2 | Completed | Dimas Fauzi Hidayat | agus.suparman, samudra.linggar | izzul | — |
| Chatbot 26Q3 Engineering Initiatives (bucket) | 2026-Q3 | Backlog | agus.suparman | agus.suparman, eko.aprianto, samudra.linggar, baghiz.firdausa | tito.amanda, izzul | README |
| Chatbot Q3 2026 Code Readiness (bucket) | 2026-Q3 | Backlog | Puji Triwibowo | baghiz.firdausa, samudra.linggar, farras.herdicho | — | README |
Priority
| Priority | Initiative | Depends on | Note |
|---|---|---|---|
| P1 | Autonomous AI Agent — Phase 2: AI-Assisted Refinement (Refiner) | — | Design: Ready (Wulan's live "Refine" prototype; Figma to follow). Blocking Data/ML refine-skill-pack dep (see External deps below); a possible duplicate P4 "Iteration" item (Qontak_AI_Agent_Research_Report.docx, likely Phase 4) is left unranked pending PM confirmation. |
| P2 | AI Agent Impact Report — Phase 1: Live Impact Report | — | Design: Not yet — PRD header marks Figma as pending; a plain-language wireframe and concept prompts exist as references only. Depends on Data/BI's per-organization activity-log datamart (blocking). |
| P3 | AI Agent Testing — Phase 1: Historical Validation | — | Design: Ready — design is finished and linked in the PRD. Depends on the AI platform squad's batch shadow-inference capacity (TPM/RPM limits) for the shared answer-evaluation engine (blocking). |
| P4 | AI Agent Knowledge — Phase 1: Conversation History | — | Design: Partial — an early design exists in the repo designer; needs a designer revisit. Depends on the AI/ML (Data & AI) team's PII-masking engine, conversation-training service, and training-status webhook that turn past chats into searchable knowledge (blocking). |
| P5 | Unified Agent Quality Scorecard — Phase 1: Settings & Rubric | — | Design: Not yet — concept prompts are prepared for the designer. Depends on AI platform (DSAI)'s scoring-engine metric definitions, but this dependency is explicitly non-blocking for Phase 1 per its own PRD's dependency table — it becomes blocking starting Phase 2. |
| P6 | Unified Agent Quality Scorecard — Phase 2: Auto-Scoring & In-Room | — | Design: Not yet — concept prompt is prepared for the designer. Depends on AI platform (DSAI)/engine team's SkillPack evaluator output contract (blocking). |
| P7 | Unified Agent Quality Scorecard — Phase 3: Analytics Report | — | Design: Partial — the dashboard is built in the analytics tool (Metabase reuse); the report host page/nav entry around it still needs design. Depends on Data/BI (Data / Analytics)'s unified Metabase dashboard + warehouse pipeline (blocking). |
| P8 | Mekari Action (AI Agent) | — | Backlog-tier (2026-07-02 append). |
| P9 | Native Integration (AI Agent) | — | Backlog-tier append (2026-07-02). Scoped Sprint-1 pull-in only — Google Calendar OAuth/booking + Google OAuth app-verification submission; portfolio rank unchanged (see sprint 01). |
| P10 | Qontak Action (AI Agent) | — | Backlog-tier (2026-07-02 append). |
| P11 | AI Agent Idle Action | — | Backlog-tier (2026-07-02 append). |
| P12 | AI Agent Monitoring | — | Backlog-tier (2026-07-02 append). |
| P13 | Bot-vs-Human Traffic Split (A/B) | — | Backlog-tier (2026-07-02 append). |
| P14 | Multi-WABA Impact | — | Backlog-tier (2026-07-02 append). |
| P15 | Meta Business Agent Integration | — | Backlog-tier append (2026-07-12), placeholder rank pending PM confirmation. Draft: Phase 1 (MBA-aware foundation) ungated; Phases 2–3 gated on MBA general availability + Indonesia service-message pricing. |
| P16 | AI Spam Gatekeeper | — | Backlog-tier append (2026-07-16), placeholder rank pending PM confirmation. Draft motivated by Meta's 2026-10-01 per-service-message billing change (see bifrost/meta-whatsapp-pricing-oct-2026, Epic BIF-8755). |
| P17 | Automation Flow Builder | — | Backlog-tier append (2026-07-17), placeholder rank pending PM confirmation. Draft: desk-validated GO (vs Sleekflow/Respond.io/WATI/Trengo/Gallabox), pre-PRD — repositions the bot tree into a unified conversation+automation engine; core risk is a live-traffic runtime migration needing an engineering feasibility spike before write-prd. |
| P18 | AI Agent Memory | CEBE | Backlog-tier append (2026-07-22); 2026-Q4 target (only Q4 row — ranked last by quarter, not importance). ANCHOR + Phase-1 PRD both READY; hard CEBE + DSAI blockers (see Cross-initiative / External deps below); Design N/A (Phase 1 flag-only). |
Adhoc / Interrupt lane
| Bucket (Epic) | 🔴 Expedite (may preempt) | 📅 Fixed-Date | 🟡 Standard (pull-in fill) | ⚪ Intangible | Tracker |
|---|---|---|---|---|---|
| Chatbot 26Q3 Engineering Initiatives (Epic BOT-4620) | A1 (Ruby/Rails Phase 1), A3 (pdfjs-dist SCA remediation) | — | A2 (Rails 8.1 / Ruby 4.0 Phase 2), A4 (subscription flag gating), A5 (Aegis no-response alert → auto fallback), A6 (stuck KB Processing 5h alert) | — | tracker |
| Chatbot Q3 2026 Code Readiness (Epic BOT-4500) | — | — | A1 (MCP), A2 (testing), A3 (hooks), A4 (agent skills), A5 (internal tooling) | — | tracker |
Stories are classed, not ranked; each bucket's tracker + ## Expedite log is canonical and this table
mirrors it. Estimates remain TBD. Open: A3's 🔴 Expedite has no ## Expedite log entry — DRI to
authorize retroactively.
Portfolio progress & forecast
Nine of the thirteen BOT initiatives read 0% done with effort_*/forecast TBD (no
DRI-confirmed man-days). Four are sized (rfc-task-breakdown-derived, no sign-off yet) — figures in
the table below. No implementor is over capacity; see capacity.md.
Headline: AI Agent Testing (P3) overflows 2026-Q3 (p85 2026-10-25) — a real sequencing conflict,
per-person schedules in status 2026-07-14.
AI Agent Knowledge stays TBD (RFC review HOLD on cross-team blockers).
% done is live for Autonomous AI Agent Phase 2 (51% as of 2026-07-20, see
status) and, from Sprint 1's close, for
AI Agent Testing — 7% (2.5 / 37.5 man-days as of 2026-07-27, see
status); a floor, since 5 merged issues carry no
breakdown task-id. Others stay — (board-done issues don't yet join breakdown tasks). The Engineering
Initiatives bucket reads 1 of 6 done (17%) as of 2026-07-27 (A3 pdfjs SCA remediation BOT-4661
merged, chatbot-fe PR #1556), effort unsized.
Branch Bot Response — Customer/Contact Field is a shipped 2026-Q2 row recorded retroactively on 2026-07-27, excluded from the Q3 narrative — 100% (11/11 stories, DRI-attested bookkeeping, not per-Story code evidence). See status 2026-07-27.
Autonomous AI Agent is At Risk despite BOT-4191 at 80/80 Done (Phase 1): production-deployed but
sandbox-gated, with unresolved staging runtime errors blocking GA — see
status 2026-06-25. Phase 1 man-days were never
recorded, so the % done below covers Phase 2 only.
| Initiative | % done | Effort (total man-days) | p85 forecast | Confidence |
|---|---|---|---|---|
| Autonomous AI Agent | 51% (12.5 md) | 24.5 (Phase 2 only) | 2026-08-18 | medium |
| AI Agent Knowledge | — | 13 | TBD | medium |
| AI Agent Testing | — | 37.5 | 2026-10-25 | medium-high |
| AI Agent Impact Report | — | 33.5 | 2026-09-18 | medium |
| Bot-vs-Human Traffic Split (A/B) | — | TBD | TBD | — |
| Mekari Action (AI Agent) | — | TBD | TBD | — |
| Native Integration (AI Agent) | — | TBD | TBD | — |
| Qontak Action (AI Agent) | — | TBD | TBD | — |
| Unified Agent Quality Scorecard | — | TBD | TBD | — |
| AI Agent Idle Action | — | TBD | TBD | — |
| AI Agent Monitoring | — | TBD | TBD | — |
| Multi-WABA Impact | — | TBD | TBD | — |
| Meta Business Agent Integration | — | TBD | TBD | — |
| AI Agent Memory | — | TBD | TBD | — |
| Branch Bot Response — Customer/Contact Field (2026-Q2, shipped) | 100% (11 of 11 stories done) | TBD (never sized) | — (rolled out 2026-07-09) | — |
| Chatbot 26Q3 Engineering Initiatives (bucket) | 17% (1 of 6 stories done) | TBD | TBD | — |
| Chatbot Q3 2026 Code Readiness (bucket) | 0% (0 of 5 stories done) | — (unsized bucket) | — | — |
QA Lanes
| Initiative | Lane | Basis | As of |
|---|---|---|---|
| Autonomous AI Agent | B | real-time chat flow + multi-org data isolation (Lane B triggers) | 2026-06-26 |
| AI Agent Knowledge | B | thin spec; triggers unknown — defaults to B | 2026-06-29 |
| AI Agent Testing | B | no Lane-B trigger; no E2E specs yet — entry bar unmet | 2026-06-29 |
| Bot-vs-Human Traffic Split (A/B) | B | routing/AB experiment; no E2E specs yet — entry bar unmet | 2026-06-29 |
| Mekari Action (AI Agent) | B | security: cross-product SSO & HMAC auth | 2026-06-29 |
| Native Integration (AI Agent) | B | money-critical: Midtrans payments; out-of-reach: third-party OAuth | 2026-06-29 |
| Qontak Action (AI Agent) | B | money-critical: deal/ticket creation | 2026-06-29 |
| Unified Agent Quality Scorecard | B | analytics/scoring; no E2E specs yet — entry bar unmet | 2026-06-29 |
| AI Agent Idle Action | B | no Lane-B trigger; no E2E specs yet — entry bar unmet | 2026-06-29 |
| AI Agent Monitoring | B | real-time: live supervisor alerts / push | 2026-06-29 |
| Multi-WABA Impact | B | out-of-reach: external Meta WABA platform | 2026-06-29 |
| Meta Business Agent Integration | B | out-of-reach: external Meta MBA platform / Thread Control API; real-time inbox handover | 2026-07-12 |
| Chatbot 26Q3 Engineering Initiatives | B | scaffolded conservative default — production tech-stack work requires a human QA gate once a story is defined | 2026-07-13 |
| Chatbot Q3 2026 Code Readiness | B | conservative validation default; QA Scope and ownership are declared per story when QA participates | 2026-07-24 |
| AI Agent Memory | B | real-time: memory read on the live agent response path; AI-dependent output (team policy); no E2E specs yet | 2026-07-22 |
| Branch Bot Response — Customer/Contact Field | B | real-time: CDP fetch on the live conversation path (2–3s SLA); security/PII: read-only customer attributes must not be logged | 2026-07-27 |
Lane A: 0 of 16 initiatives (target 20–50% in Lane A). Every classified BOT initiative has a Lane-B trigger and/or no E2E specs yet, so the Lane-A entry bar (100% E2E, spec-mapped) is unmet across the board.
Team policy: initiatives that depend on AI services stay Lane B — AI-powered features are non-deterministic/probabilistic and need human judgment to verify alignment. Targeted automation is still added for specific testcases (e.g. CRUD configuration & functionality, UI changes, hide/show validation, permission validation).
Capacity summary
See capacity.md for the full per-implementor table.
- No implementor is over capacity. The binding constraint is Baghiz Firdausa (FE) at 0.55×; five of
eight active/draft initiatives are unstaffed, so headroom exists once external blockers clear.
Per-person figures:
capacity.md. - Chatbot 26Q3 Engineering Initiatives is intentionally omitted from numeric load: its stories have no named implementor or DRI-confirmed effort yet. Add its allocation only when a specific story is staffed and pulled under the bucket rule.
- Code Readiness is also omitted from numeric load because its work is unsized. Its current
contributors are mirrored in capacity as
TBD; QA is added only for stories with QA Scope.
Cross-initiative dependencies
- AI Agent Memory (P18) is blocked by Customer Event-Based Engine (CEBE) (CDP squad, TF-3302) — the Central DB + Retriever/query layer must be live in staging before Memory's BUILD gate G0; Memory is CEBE's named flagship downstream consumer ("Agentic AI reads CEBE memory — Q4 2026"). Tracked in
ai-agent-memory/README.mdfrontmatterdepends_on: [customer-event-based-engine-cebe].
External & cross-squad dependencies
| Initiative | Blocking dependency | Owner (squad / vendor) | Status |
|---|---|---|---|
| Autonomous AI Agent | Upstream refine-skill-pack suggestion-engine endpoint (Phase 2 Refiner) | Data / ML | 🔴 |
| Autonomous AI Agent | Structured guardrails array on the AI-service setup-agent contract (+ migration of existing setup agents) — without it Refine cannot split the merged guidance string back into fields; DSAI committed 2026-07-21 to pick it up, no date | AI platform (DSAI) | 🔴 |
| AI Agent Impact Report | Per-organization activity-log datamart the report reads from | Data / BI | 🔴 |
| AI Agent Impact Report | Per-participant room assignment-source tracking (AAA · round robin · assign by bot · get chat · handover · manual from room · contact assignee) — needed for the unintended-room metric; not stored in any table today (note) | Chat squad (Burhanudin Hakim) | 🟡 |
| AI Agent Testing | Batch shadow-inference capacity (TPM/RPM limits) — shared answer-evaluation engine | AI platform | 🔴 |
| AI Agent Knowledge | PII-masking engine, conversation-training service + training-status webhook | AI/ML (Data & AI) team | 🔴 |
| Unified Agent Quality Scorecard | SkillPack engine evaluator output contract (Phase 2 Auto-Scoring) | AI platform (DSAI) / engine team | 🔴 |
| Unified Agent Quality Scorecard | Unified Metabase dashboard + warehouse pipeline (Phase 3 Analytics Report) | Data / BI (Analytics) | 🔴 |
| AI Agent Memory | CEBE Central DB + Retriever/query layer live in staging (TF-3302) + this phase's consumer requirements landed in the CEBE RFC (query ≤1–2s, DSAI auth, AI-consumer PII allow-list) | CDP squad (Task Force) | 🔴 |
| AI Agent Memory | CEBE retriever client + context injection + memory telemetry in the response envelope — signed contract is BUILD gate G0 | AI platform (DSAI) | 🔴 |