Launch HN: Manaflow (YC S24) – Automate repetitive office work in tables
Manaflow is an AI automation tool for SMBs that simplifies workflows via a spreadsheet interface, allowing non-technical users to automate tasks efficiently and significantly reduce manual workloads.
Manaflow is an AI automation tool designed to streamline workflows for small to mid-sized businesses (SMBs). It operates through a spreadsheet interface where each column represents a step in a task and each row corresponds to an AI agent executing that task. The tool allows users to program workflows using natural language, making it accessible to non-technical users. This eliminates the need for coding skills and enables users to automate tasks such as data retrieval, API integration, and content processing with a single click. The platform has proven effective in reducing manual workloads significantly; for instance, one customer reduced a 20-hour task to just 20 minutes. Manaflow also includes features like OAuth connections, web crawling, and data transformation tools, which enhance its utility for various business processes. The creators are exploring two methods for programming workflows: using natural language instructions and a Notion-inspired editor for defining Python tools. They invite feedback and insights from users to improve the platform further.
- Manaflow automates workflows for SMBs using a spreadsheet interface and AI agents.
- Users can program tasks in natural language, making it accessible to non-technical individuals.
- The tool significantly reduces manual workload, exemplified by a customer cutting a 20-hour task to 20 minutes.
- It includes various built-in tools for data retrieval, API integration, and content processing.
- The creators are seeking user feedback to enhance the platform's functionality.
Related
Show HN: Uniflow - A fast multipurpose workflow engine
Uniflow is a high-performance workflow engine known for managing tasks of varying lengths and allowing on-the-fly specification modifications. It seamlessly integrates new nodes for enhanced features. Find more details on Uniflow on its GitHub Repository.
Maestro: Netflix's Workflow Orchestrator
Netflix introduces Maestro, a versatile workflow orchestrator on GitHub. Maestro handles large-scale workflows efficiently, supporting various use cases with scalability, reusable patterns, and configurable features. It simplifies workflow management and offers flexibility.
Diverse ML Systems at Netflix
Netflix utilizes data science and machine learning through Metaflow, Fast Data, Titus, and Maestro to support ML systems efficiently. The platform enables smooth transitions from prototypes to production, aiding content decision-making globally.
Using Agents to Not Use Agents: How we built our Text-to-SQL Q & A system
Ask-a-Metric is a WhatsApp-based AI tool for SQL queries in the development sector, improving accuracy and efficiency through a pseudo-agent pipeline, achieving under 15 seconds response time and low costs.
Show HN: AutoDocument – Multi-Source Document Generation
AutoDocument is an open-source tool for automating document processes, featuring advanced templating, multi-step workflows, and support for various file storage options, receiving positive user feedback for its capabilities.
- Users find the spreadsheet interface confusing and suggest clearer representation of tasks and subtasks.
- There are questions about the tool's functionality, including the need for conditionals and integration with existing spreadsheet platforms like Google Sheets or Excel.
- Some commenters express skepticism about the tool's value and effectiveness, particularly in understanding the complexities of non-technical roles.
- Technical issues with the demo, such as slow performance and loading errors, are highlighted by multiple users.
- Feedback suggests a preference for a more intuitive flowchart or node-based interface over the current spreadsheet design.
So many AI startups and I have yet to see one that makes sense for me. But I don't blindly trust any output from any LLM, so that's probably the reason.
People expect that rows represent observations and columns represent variables. Along those lines, would it not be more accurate to say each row represents an instance of a task and column represents a sub-task or step in that task?
"each row corresponds to an AI agent executing a task" just... doesn't make sense. The rows exist before you press the "execute" button, after all. The agent executing the (generic) task is something that happens on or with the sheet.
If the probability of an LLM making a mistake = 5% and you have 10 steps then the accuracy of the overall workflow is 60%. Which is useless. Even if we have major advancements in the performance of LLMs and it drops to 1% then still the overall workflow is 90% which is poor.
So what is the plan here ? There is a limit to how many tasks in businesses can tolerate so much inaccuracy.
did you bother finding out where those spreadsheets come from, internal systems, external reports from vendors, are they consolidated bank statements, inventory counts and status, amazon/shopify inventory status
your ai tool should enable them to work with these spreadsheets as a starter.
I totally agree with vector_spaces comment, having a AI agent create a new workflow and train business manager on using it is a dead end. They have had the last 30years to explore VBA, Access and the other tools Microsoft comes with, and they last thing they will do is understand python the way your demo shows
Also: are there conditionals? So you can skip a step/column if not needed, or repeat as many times as needed?
Console has errors:
> failed to load resource: the server responded with a status of 422 () clerk.browser.js:2 Uncaught (in promise) Error > at s._fetch (clerk.browser.js:2:48584) > at async X._baseMutate (clerk.browser.js:2:49256) ingest/static/recorder.jsv=1.139.3:1
> Failed to load resource: the server responded with a status of 404
I have more comments/feedback if you're interested (mostly UX).
My feedback: approach this problem, solve the problem, then use a technique. Show a repetitive work that someone does, and let the viewer watch machine doing it automatically.
In other words, your aim is right, but knowledge you possess is distracting you to solve it neat and clean.
I wish you luck but honestly it seems like you have not done the ground work behind what operation managers actually do.
Tech people seem to have this cluster of assumptions that leads them to conclude that there aren't intelligent people in non-tech roles, and that these people can't see obvious optimizations of their roles because of their lack of coding skills or something.
The reality is usually that there are layers upon layers of hidden complexity in these businesses -- ones that require a mix of domain expertise and deep awareness of the business and human context to effectively manage. Often you won't even have so much as heuristics to go on.
That isn't to say that automation and AI can't be leveraged to great effect, but it's simply not going to be the drop-in solution you claim it is. Claiming it is in this way -- esp with your smug lip-service to job annihilation -- is going to rub people the wrong way.
Instead you should re-message this around augmentation and making jobs easier so that people can focus on other concerns, and reducing costly errors introduced by manual process.
It's unclear who exactly your target is, but if you are going for e.g. parts manufacturers, local shipping & logistics companies, small CPG brands, then the examples in your videos are all wrong. Get the weird Fibonacci stuff out of the side panel, clean out any junk that says "test" and use polished examples related to reconciling purchase orders, forecasting demand for a new product line, managing production schedules, etc. You need to make the value this thing adds accessible to intelligent people who don't have a CS degree.
Related
Show HN: Uniflow - A fast multipurpose workflow engine
Uniflow is a high-performance workflow engine known for managing tasks of varying lengths and allowing on-the-fly specification modifications. It seamlessly integrates new nodes for enhanced features. Find more details on Uniflow on its GitHub Repository.
Maestro: Netflix's Workflow Orchestrator
Netflix introduces Maestro, a versatile workflow orchestrator on GitHub. Maestro handles large-scale workflows efficiently, supporting various use cases with scalability, reusable patterns, and configurable features. It simplifies workflow management and offers flexibility.
Diverse ML Systems at Netflix
Netflix utilizes data science and machine learning through Metaflow, Fast Data, Titus, and Maestro to support ML systems efficiently. The platform enables smooth transitions from prototypes to production, aiding content decision-making globally.
Using Agents to Not Use Agents: How we built our Text-to-SQL Q & A system
Ask-a-Metric is a WhatsApp-based AI tool for SQL queries in the development sector, improving accuracy and efficiency through a pseudo-agent pipeline, achieving under 15 seconds response time and low costs.
Show HN: AutoDocument – Multi-Source Document Generation
AutoDocument is an open-source tool for automating document processes, featuring advanced templating, multi-step workflows, and support for various file storage options, receiving positive user feedback for its capabilities.