Tejas is a system of 129 AI agents organised across 11 specialist teams — covering marketing, sales, product, engineering, design, advisory, and operations. It is operated personally by two founding partners and functions as an AI-native growth department for mid-market companies. Tejas replaces the need to hire multiple senior executives or separate agency retainers across functions.

Is the 90-Day Growth Blueprint really free?

Yes. The Blueprint is fully funded by Appetals Solutions. It includes a Diagnostic Audit, a half-day Leadership Bootcamp, and a 90-Day Action Plan — all at zero cost and with no obligation to proceed to a retainer.

Who actually does the work — the partners or AI agents?

Both. Ishwar Jha designs the operational strategy and operates every engagement cycle personally. Tejas — 129 AI agents across 11 specialist functions — executes the operational workflows under his direction. Neither delegates down.

Are we too small for this?

The Blueprint is designed for companies between ₹50 crore and ₹500 crore in revenue — mid-market businesses where growth has stalled and the board or investors are watching results every quarter.

What does performance-linked pricing mean?

Retainer pricing scales with your results. You do not pay a fixed monthly fee regardless of output. If Tejas misses targets, you pay less. Tejas earns when you grow.

How is Tejas different from hiring a CMO or an agency?

A CMO hire takes 4–8 months to recruit and 3–6 months to ramp, at ₹1.2–2.4 crore per year before results. Three separate agencies cost ₹80L–1.5 crore per year and take months to align. The Blueprint gives you a running growth system in 90 days at no upfront cost, operated by a founding partner with 30 years of experience.

Do we need an internal team to make this work?

No internal build-out is required. Tejas operates as your growth function. We handle execution; you handle decisions and approvals.

What happens after the 90-Day Blueprint?

Founders who want to continue move to a Growth Acceleration retainer — a performance-linked engagement where Ishwar continues operating the system on your behalf across five playbooks: growth stack architecture, sales system engineering, demand generation, retention operating system, and investor narrative and board reporting.

Chapter 13: Lumen Why MCP Integrations

MCP stands for Model Context Protocol, the standard that lets Claude Code connect to external tools and data sources. Lumen uses 10 MCP servers. None are required to run a workflow. Each one adds data that improves evidence quality and unlocks specific capabilities.

Go through the chapter to understand what each integration adds to your results and when it is worth setting up.

PostHog

What it unlocks: PMF scoring in W1, behavioral forensics in W2 and W6, feature adoption signals in W4, post-launch monitoring in W5.

Without it: W1 runs in PARTIAL mode. SignalMonitor cannot score PMF. DiscoveryOS and MarketIQ still run, but the PMF section is blank and evidence quality is LOW for all signal-dependent sections.

Worth setting up: Yes, before your first W1 run. PMF scoring is the core capability of Lumen. Everything else builds on it.

What you need: PostHog project API key (POSTHOG_PROJECT_API_KEY). Add it to .env.

# In .env
POSTHOG_PROJECT_API_KEY=phc_xxxxxxxxxxxxxxxxxxxx
Then in lumen-setup.json:
"posthog": { "enabled": true, "host": "https://app.posthog.com" }

Minimum useful data: 30 days of event data. 90 days is ideal for retention curves.

Supabase

What it unlocks: Knowledge Graph persistence, decision history, outcome tracking IDs, 30/60/90-day follow-up across sessions.

Without it: Every Lumen session starts from scratch. Decisions are not logged. Outcome tracking IDs exist only for the current session. Prior quarter data is unavailable for strategy comparison.

Worth setting up: Yes, before your second W1 run. Without Supabase, you are running Lumen as a one-off analysis tool instead of a continuous PM operating system.

What you need: SUPABASE_URL and SUPABASE_ANON_KEY. Create a free Supabase project at https://supabase.com.

# In .env
SUPABASE_URL=https://xxxxxxxxxxx.supabase.co
SUPABASE_ANON_KEY=eyJh……………………………….....
All Supabase tables use Row Level Security scoped to your workspace_id. Your data does not mix with other workspaces.

Upstash

What it unlocks: Session context survives Claude Code restarts. A workflow can continue across multiple sessions without re-entering context.

Without it: Closing Claude Code clears the session. Long workflows (W3 strategy, W5 launch) may need context re-entry if the session is interrupted.

Worth setting up: Yes, if you regularly work across multiple Claude Code sessions. Low effort to set up (two credentials, five minutes).

What you need: UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN. Create a free Redis database at

https://upstash.com.
# In .env
UPSTASH_REDIS_REST_URL=https://xxx.upstash.io
UPSTASH_REDIS_REST_TOKEN=AxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxQ=

Slack

What it unlocks: Reports delivered to a Slack channel after each workflow. Level 2 oversight gate notifications in Slack (you can read the gate without being in the terminal). Reminders when a gate is about to time out.

Without it: Reports are available only in the Claude Code session. You must be in the terminal to see and respond to Level 2 gates.

Worth setting up: Yes, for any team where more than one person needs to see workflow outputs or respond to gates.

What you need: SLACK_BOT_TOKEN (starts with xoxb-) and a channel name.

# In .env
SLACK_BOT_TOKEN=xoxb-xxxxxxxxxxxx-xxxxxxxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxx
// In lumen-setup.json
"slack": { "enabled": true, "ops_channel": "#product-ops" }

HubSpot

What it unlocks: CRM-based churn signals for SignalMonitor and GrowthIQ. Renewal dates and account health scores from your CRM. Exit signals from support tickets.

Without it: Churn analysis relies entirely on behavioral signals from PostHog. This is workable but misses the CRM layer — support tickets, renewal pipeline, account owner notes.

Worth setting up: Yes, for Growth tier. If you have HubSpot in active use for your sales or CS motion, connecting it materially improves W2 and W6 churn attribution accuracy.

What you need: HubSpot API key. Configure via /lumen:setup.

Stripe

What it unlocks: Billing-accurate NRR decomposition in GrowthIQ. Expansion, contraction, and churn broken down by MRR rather than estimated from user counts.

Without it: GrowthIQ estimates NRR from PostHog user counts and a revenue-per-seat assumption. This is often directionally correct but imprecise.

Worth setting up: Yes, for Growth tier, especially for W6 Churn Analysis and W3 strategy (where pricing model work benefits from real billing data).

What you need: Stripe secret key. Configure via /lumen:setup.

Figma

What it unlocks: UXLayer reads design specs directly from Figma during W4 Feature Validation and W5 Launch. Accessibility flags are applied against the actual design, not a hypothetical spec.

Without it: UXLayer produces an interaction design spec from requirements. It cannot verify against a specific Figma design file.

Worth setting up: Yes, for the Scale tier, when UXLayer is part of your workflow. Low value before you have Figma designs to reference.

What you need: Figma personal access token. Configure via /lumen:setup.

GitHub

What it unlocks: EcosystemOS reads pull request velocity, open issue volume, and contributor activity when designing a developer platform strategy.

Without it: EcosystemOS uses a manually provided development context. For most use cases, GitHub is not required.

Worth setting up: Only for the Enterprise tier, specifically for W3 strategy runs that include a developer API or platform track.

What you need: GitHub personal access token with repo scope. Configure via /lumen:setup.

Sentry

What it unlocks: OpsCommand reads error rates when assessing crisis severity in W2 and W6. A Sentry spike coinciding with a churn increase is strong evidence of product quality churn.

Without it: OpsCommand estimates crisis severity from behavioral signals only. Error rate correlation is unavailable.

Worth setting up: Useful for any team that already uses Sentry actively. If you do not use Sentry, it is not worth setting up just for Lumen.

What you need: Sentry auth token and organization slug. Configure via /lumen:setup.

Postman

What it unlocks: EcosystemOS reads API test coverage when assessing developer platform readiness in W3 Enterprise runs.

Without it: Developer platform readiness is assessed from manually provided context.

Worth setting up: Only for the Enterprise tier, specifically for developer platform tracks. Rarely needed outside that context.

Quick Reference: Value by Workflow

MCP	W1	W2	W3	W4	W5	W6
PostHog	Critical	Useful	Useful	Useful	Monitoring	Critical
Supabase	KG	KG	KG	KG	KG	KG
Upstash	Session	Session	Session	Session	Session	Session
Slack	Reports	Reports	Reports	Reports	Reports	Reports
HubSpot	Churn signals	Critical	OKR context	—	CRM	Critical
Stripe	—	NRR	Pricing	—	Pricing	Critical
Figma	—	—	—	UX spec	UX spec	—
GitHub	—	—	Platform	—	—	—
Sentry	—	Crisis	—	—	—	Crisis
Postman	—	—	Platform	—	—	—

KG = Knowledge Graph persistence (applies across all workflows when Supabase is connected).

Chapter 1: What Lumen Does

Chapter 2: Lumen Installation and First Launch

Chapter 3: Lumen Your First 15 Minutes

Chapter 4: Lumen The Mental Model

Chapter 5: Lumen Evidence Quality: Reading the Grades

Chapter 6: Lumen Oversight Gates: When and Why Lumen Pauses

Chapter 7: Lumen W1: PMF Discovery

Chapter 8 — Lumen W2: PMF Recovery / Churn Crisis

Chapter 9: Lumen W3: Quarterly Strategy

Chapter 10: Lumen W4: Feature Validation

Chapter 11: Lumen W5: GTM Launch

Chapter 12: Lumen W6: Churn Analysis