This article is a part of Startup Spotlight, a series that features young, up-and-coming startups.

Photo credit: IFarmer

What started as a side project for urban rooftop farming in 2018 quickly hit a wall of scalability. The co-founders of iFarmer leveraged their decade of experience in rural agriculture and pivoted, refocusing on the foundational challenges faced by Bangladesh’s smallholder farmers.

😟 Problem

Smallholder farmers, representing over 80% of Bangladesh’s agricultural population, are often caught in a poverty cycle. A lack of formal credit pushes them toward high-interest debt.

Limited market access and unfair pricing from middlemen strip them of their profits, keeping them in a state of financial instability.

💡 Solution

IFarmer offers a comprehensive platform that supports farmers at every stage of the agricultural cycle. The company aims to provide affordable loans, quality inputs, and fair market access. Its services include:

• Farmer financing that bridges the capital gap with low-cost, timely funding.
• An input business to deliver premium seeds and fertilizers to rural communities.
• Advisory services that provide weather alerts and personalized training.
• An output business that buys crops directly from farmers to guarantee a reliable market.

Photo credit: IFarmer

📊 Market size

The agricultural sector in Bangladesh is a US$52 billion economy that employs 40% of the national labor force. This market is driven by 20 million farmers, of whom a staggering 80% are smallholders. The agricultural input market alone is valued at US$27 billion, with nearly half of it remaining unorganized.

🤝 Team

• Fahad Ifaz. Co-founder and CEO.
• Jamil M Akbar. Co-founder and COO.

🚀 Traction

• Generated US$50 million in sales of agricultural inputs.
• Moved US$140 million in agricultural commodities through its supply chain.
• Facilitated US$96 million in financing for farmers.
• Launched Krishop, an agricultural ecommerce platform with over 20,000 active retailers.
• Developed the Folon app to directly connect farmers with its services, such as community support and personalized advisory. 

🏆 Competition

IFarmer operates in Bangladesh’s emerging agritech sector alongside competitors like WeGro Global, Fashol, and Krishi Shwapno.

The company differentiates itself through deep, on-the-ground farmer engagement. It hosts monthly courtyard meetings and maintains a physical network of over 1,200 iFarmer Centers.

💰 Financials

The company generates revenue from multiple streams, including commissions on financing and margins on the sale of inputs and products. It also charges service fees to institutional buyers for aggregated and quality-assured supply.

IFarmer has raised US$6.53 million to date and is planning a new round to raise US$5 million.

This piece was written with the help of AI and edited by our staff based on information provided by the startup.

Want to get your startup featured? Fill in the survey here.

This article summarizes an episode of Aakash Gupta’s video series featuring Frank Lee, principal product manager at Amplitude.

Image credit: Arsal Ysfin

Frank Lee, principal product manager at Amplitude, argues that software development has moved past manual data analysis. Automating these routine tasks changes the job completely, leading to an era of “vibe PMing.” In this new world, success comes from a manager’s taste and vision, rather than their ability to just churn through paperwork.

However, Lee warns that insight is useless without speed. For automation to matter, it must compress the gap between identifying a problem and fixing it. By integrating AI tools directly into his workflow, he ensures teams can move instantly from diagnosis to execution.

Rethinking the product system

To make this possible, Lee rethinks how information is organized. Most product leaders struggle to make AI find information across the scattered software their companies use. Lee avoids this by organizing roadmaps, contexts, and notes into local files within his code editor, allowing AI tools to access everything simultaneously.

Lee says, “On the left-hand side [of my code editor], I have a bunch of contexts that I’ve already actually aggregated… within Claude Code or within Cursor, I can easily refer to some of those pieces of context, brainstorm about them, and draft a new spec.”

Bridging integration gaps
Beyond organizing context, Lee also addresses workflow friction. He observes that product managers often waste time manually bridging information gaps between tools. To eliminate that inefficiency, he writes custom scripts that pull data from specialized applications into his central workflow.

“Granola [a meeting notes tool] actually does not have a dedicated MCP [command palette] right now. So I tried to hack Claude Code to build some type of automation,” Lee explains. “I basically could run a command to pull in my recent Granola notes using the script we wrote.”

Automating data insights

Similarly, investigating unexpected metrics by hand can consume entire weekends. To avoid this, Lee outlines a five-step process that automates the heavy lifting:

• Chart analysis: Give an agent a link to a chart. It sorts through the data, finds what’s unusual, and guesses why numbers changed.
• Automated reporting: Give an agent access to dashboards. It summarizes the main findings and problems, so you don’t have to check them by hand.
• Summarizing feedback: The agent gathers feedback from all sources (Zendesk, Gong, Slack). It then groups similar comments to find the main problems.
• Creating product documents: Take the results of the analysis and give it to a document template. The agent writes a first draft of the plan in minutes.
• Prototyping and sending tasks: Simple ideas can be turned into early models in the agent’s code editor. Harder tasks are sent to teams through Linear.

“What I would have had to do manually to investigate… the agent did it in a minute and a half,” Lee explains. “I’ve automated basically all of my weekly business reviews.”

Defining the automated workflow

Taken together, this system removes bottlenecks created by human-dependent review processes. Rather than relying on managers to read every chart and dashboard, Lee assigns defined roles to AI:

• Analysis reads charts to find unusual patterns and explains why numbers changed.
• Reporting summarizes weekly progress automatically, so managers do not have to check every dashboard.
• Building turns written ideas into early code examples or sends tasks directly to the developers.

The cost of system complexity
But giving an AI agent access to too many data sources also often creates confusion rather than clarity. Lee warns that overloading the system with irrelevant connections slows down response times and degrades the quality of answers.

“Sometimes people get excited, and they connect a bunch of MCP [tool integration] servers,” Lee argues. “If you have a huge number of servers connected… they start being provided as context to the model on a bunch of different queries that might not be relevant.”

Optimizing agent performance
Engineers are addressing these performance issues by moving away from “always-on” connections. New systems use retrieval methods to activate specific tools only when the user’s request demands them.

This approach marks a shift toward context-aware computing, where, as Lee notes, the system dynamically loads instructions and prompts “only when the model thinks it’s relevant” to execute the task at hand.

⚖️ The other side:

• While “vibe PMing” emphasizes intuition over paperwork, 2024 research from Harvard Business School indicates that AI cannot reliably substitute for human judgment in high-stakes decisions, finding that AI assistants actually lowered the performance of some business owners by 8%.
• Although Lee argues for automating weekly reviews and chart analysis, McKinsey & Company reports that “inaccuracy” remains the top risk for GenAI adoption, with only 23% of organizations reporting they have successfully implemented guardrails against hallucinations.
• While aggregating local context files for AI tools increases speed, the 2024 Cisco Data Privacy Benchmark Study reveals that 27% of organizations have temporarily banned GenAI applications due to data privacy risks, implying that Lee’s method of feeding sensitive internal roadmaps into third-party tools likely violates enterprise compliance policies.

This Too Long; Didn’t Listen (TL;DL) summary was created with the help of AI and edited by our staff. Read all summaries here.