How a B2B SaaS Company Built Its Agent Product on LeafCraft
By Khoushik Reddy Ananth
- Industry: B2B SaaS
- Business area: customer success
- Use case: an agent product runs customer success follow ups and books meetings end to end.
A B2B SaaS company wanted to sell a product in which agents coordinate customer success for its own customers.
Building the orchestration in house would have delayed launch by months. Governance and handoffs between agents and people would have had to be built from scratch, and every new use case would have taken months of engineering. Without a predictable cost per agent, there was also no sound way to price the product.
The company built its whole agent product on LeafCraft instead. It now runs more than 12 agents in production, with AI governance built in, and launches a new use case about 30% faster than it could by building in house.
Why building it in house was a hard problem
The agents were the visible part of the product. Underneath them the company would have needed orchestration, governance and handoffs between agents and people, all built from scratch.
That would have delayed launch by months, and every new use case would have taken months of engineering after that. Without a predictable cost per agent, there was no sound way to price the product.
The company needed enterprise intelligence it could build a product on: governed agents, a known cost for each one, and one shared history for every account.
What LeafCraft did: one AI agent management platform under the product
The company built its whole agent product on LeafCraft, instead of building orchestration and governance itself. The product runs on all five of the platform's pillars.
Human-AI collaboration, with AI and people as one team
More than 12 agents run follow ups and book meetings end to end through the product's CRM and calendars, using account signals from Clay and LinkedIn and tool integrations through Composio.
When an account needs a human touch, the agent hands it to a customer success manager in Slack. In this kind of human-AI collaboration, agents handle the routine follow ups and people handle the relationships.
AI governance that comes built in
AI governance comes built in, including the rules and handoffs between agents and people, so the company did not have to build them from scratch. New use cases are set up through configuration rather than months of new code.
AI cost control and a predictable cost per agent
AI cost control caps every agent's cost, which gives the company a predictable cost per agent to price its own product on.
One view, and AI agent management in one place
All of the agents run on one platform, so AI agent management for every agent in production happens in one place.
Enterprise memory and institutional knowledge shared by agents and people
Agents and customer success managers share the same account history, so whoever picks up an account, agent or person, knows what has already happened. That shared history is the company's institutional knowledge of its accounts.
How a typical case moves through the team
Take one account: the main contact has changed jobs, just before renewal.
1. What the agent did
The follow up agent sees from the CRM and LinkedIn signals that the main contact at a customer account has changed jobs, and that product usage has dropped over the past month. It drafts an email to the new contact and proposes a meeting time from the calendar.
2. Why it went to a person
The account is up for renewal soon, and the drop puts it at risk. Accounts at risk are handed to a customer success manager, so the agent passes it over in Slack with the account history and its draft.
3. What the person did
The customer success manager rewrites the email to mention a feature the customer asked for last quarter, and asks the agent to set up a call with both the new contact and the account's executive sponsor.
4. How it was resolved
The agent books the meeting and sends reminders. After the call, the manager records that the renewal is back on track.
5. What LeafCraft recorded
The signal, the agent's draft, the manager's change and why she made it, and the outcome are all kept in the shared account history on LeafCraft. Whoever touches the account next, agent or person, sees the full story.
From knowledge retention to decision intelligence
Knowledge retention no longer depends on any one customer success manager, because the history stays with the account.
Over time the company's enterprise memory builds up a record of which signals point to risk. That record gives the team decision intelligence about its accounts.
The result: a faster launch and less infrastructure work
The company launches a new use case about 30% faster than it could by building in house, runs more than 12 agents in production, and spends about 30% less engineering effort on agent infrastructure.
Figures are as reported by the customer.
How the LeafCraft platform helped
Each problem the company started with was answered by a part of the platform.
- Building the orchestration in house would have delayed launch by months. The company built its whole agent product on the platform instead.
- Governance and handoffs between agents and people would have been built from scratch. On LeafCraft, AI governance and those handoffs come built in.
- Every new use case would have taken months of engineering. New use cases are now set up through configuration.
- Without a predictable cost per agent, there was no sound way to price the product. AI cost control caps every agent's cost, which gives the company a cost per agent to price on.
- Account knowledge would have depended on individual managers. Enterprise memory gives agents and customer success managers the same account history.
About LeafCraft
LeafCraft is the platform for the Hybrid Intelligent Enterprise, where AI agents and people work as one team, each with a job description, under one set of rules. Enterprises run the agents they've built or bought (from SaaS or AI agent vendors), or build new ones on LeafCraft. It works with the workflow and automation tools they already use, whether built in house, bought as software or custom developed.
Human-AI collaboration on LeafCraft rests on four pillars:
- Governance: under LeafCraft's AI governance, every agent and person has a job description, a named owner, clear rules and approvals, and no one checks their own work.
- Cost control: with AI cost control, the cost of every task is known and capped before it runs.
- One view: enterprises see every agent, built or bought, alongside their people on one roster, which keeps AI agent management in one place.
- Enterprise memory: every decision and its reason is recorded and stays with the enterprise. Knowledge retention is built in, and the record becomes institutional knowledge that supports decision intelligence.
People and AI as one team. You own the rules, memory and budget.
If you are planning the move from AI tools to AI teammates, we would be glad to show you how it works. Book a conversation.
Frequently asked questions
What does Human-AI collaboration look like in customer success?
Agents run the routine follow ups and book meetings end to end. When an account needs a human touch, the agent hands it to a customer success manager in Slack, so people handle the relationships.
How does AI governance work in a product built on LeafCraft?
It comes built in, including the rules and handoffs between agents and people. The company did not have to build them from scratch.
What does an AI agent management platform do for a company building an agent product?
It carries the orchestration and governance underneath the product. All of the agents run on one platform, so AI agent management for every agent in production happens in one place.
How does AI cost control help with pricing an agent product?
Every agent's cost is capped, which gives the company a predictable cost per agent to price its own product on.
How do the agents support institutional knowledge and knowledge retention?
Agents and customer success managers share the same account history. Whoever picks up an account knows what has already happened, so nothing depends on one person's memory.
Where does decision intelligence come in?
The shared history builds up a record of which signals point to risk. The team uses it to judge which accounts need a person.
Can a company build its own agent product on LeafCraft?
Yes. This company built its whole agent product on LeafCraft instead of building orchestration and governance itself. New use cases are set up through configuration.
What results did the company report?
It launches a new use case about 30% faster than it could by building in house, runs more than 12 agents in production, and spends about 30% less engineering effort on agent infrastructure.
Is this kind of enterprise intelligence only for B2B SaaS?
No. LeafCraft is a horizontal platform, so the same five pillars apply in any industry and any process.
What is LeafCraft?
LeafCraft is an AI agent management platform for the Hybrid Intelligent Enterprise. AI agents and people work as one team, each with a job description, under one set of rules, and the enterprise owns the rules, memory and budget.
Does LeafCraft work with the agents and tools an enterprise already has?
Yes. Enterprises run the agents they've built or bought, from SaaS or AI agent vendors, or build new ones on LeafCraft. It works with the workflow and automation tools they already use, whether built in house, bought as software or custom developed.
What happens to the decisions agents and people make on LeafCraft?
Every decision and its reason is recorded and stays with the enterprise. That record is the enterprise's institutional knowledge, and it is what makes knowledge retention and decision intelligence possible.