The workflow orchestration tools I've used over the past have been consistently unsatisfying, so I've been building my own. With Coflux (https://coflux.com), workflows are defined declaratively in plain Python with decorated functions (tasks). Workers connect to the orchestration server and get assigned work - calls to other tasks get intercepted and then re-scheduled by the server onto (potentially different) workers. Tasks are executed in pre-warmed, isolated processes, with low latency.
Beyond standard features (retries, caching, timeouts - enabled with attributes on the decorator), Coflux supports more novel features - like suspense (where a task can choose to go to sleep and get restarted when a result it depends on becomes available), memoisation (where steps within a run are aggressively cached so that you can re-run steps in a workflow without re-running upstream steps), and the ability to re-run a step in a different workspaces (with updated code, or in a different environment).
It turns out this works great for implementing agentic systems - you can provide references to tasks as tools to an LLM call and have the AI drive - tasks can be easily sandboxed. And Claude is very capable of using the CLI to interact with the orchestration server to submit workflows, investigate failed runs, make updates to workflows and re-run steps.
I'm trying to make sure it's easy to try out - there's a self-contained CLI that can be used to start the server (a single Docker container), run worker processes, and then interact with the server. The dev mode automatically restarts the workers as you make local changes. There's also a hosted UI for observing runs in real-time, where you can see the execution graph, access logs/metrics/assets/etc - it works without creating an account - the browser interacts with your orchestration server directly.
We're building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens.
Our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and appropriate responses to more dangerous or more antibiotic resistant strains. We have developed a unique solution to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
I'm looking for an experienced full-stack (/'product') engineer to join our small engineering team - initially to focus on building out a novel interactive tree-based UI. There are some interesting challenges throughout the stack. We're using Python, GraphQL, React/TypeScript, Postgres and AWS, but open minded to adopting technologies that make sense.
Ideal candidates would:
- Have an interest in working in BioTech/HealthTech (experience not necessary)
- Have a strong academic background
- Be based in/around London
- Be self-motivated, and have experience working in a high-output team
- Mention these things when getting in touch (and not be CC-ing every e-mail address on this page!)
I think Maslow's Hierarchy of Needs is good place to get inspiration for this. It's guided my last two job roles in agritech and biotech. But I'm becoming aware that there seems to be an (inverse) correlation between how much money/funding is available as you go down the triangle.
We're building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens.
Our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and appropriate responses to more dangerous or more antibiotic resistant strains. We have developed a unique solution to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
I'm looking for an experienced full-stack (/'product') engineer to join our small engineering team - initially to focus on building out a novel interactive tree-based UI. There are some interesting challenges throughout the stack. We're using Python, GraphQL, React/TypeScript, Postgres and AWS, but open minded to adopting technologies that make sense.
Ideal candidates would:
- Have an interest in working in BioTech/HealthTech (experience not necessary)
- Have a strong academic background
- Be based in/around London
- Be self-motivated, and have experience working in a high-output team
- Mention these things when getting in touch (and not be CC-ing every e-mail address on this page!)
Whoops - thanks for catching this. Earlier iterations of this blog post used an different schema where `size` had been accidentally specified as a `number`. While we changed the schema, we hadn't re-run the prompt. It should be fixed now!
Their example here is really weak overall IMO. Like more than just that typo. You also probably wouldn’t want a “name” string field anyway. Like there’s nothing stoping you from receiving
{
name: “the brown one”,
size: “the espresso cup”,
… }
Like that’s just as bad as parsing the original string. You probably want big string union types for each one of those representing whatever known values you want, so the LLM can try and match them.
But now why would you want that to be locked into the type syntax? You probably want something more like Zod where you can use some runtime data to build up those union types.
You also want restrictions on the types too, like quantity should be a positive, non-fractional integer. Of course you can just validate the JSON values afterwards, but now the user gets two kinds of errors. One from the LLM which is fluent and human sounding, and the other which is a weird technical “oops! You provided a value that is too large for quantity” error.
The type syntax seems like the wrong place to describe this stuff.
I feel like that's just a documentation bug. I'm guessing they changed from number of ounces to canonical size late in the drafting of the announcement and forgot to change the output value to match.
There would be no way for a system to map "grande" to 16 based on the code provided, and 16 does not seem to be used anywhere else.
We're building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens.
Our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and appropriate responses to more dangerous or more antibiotic resistant strains. We have developed a unique solution to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
I'm looking for an experienced frontend (or full-stack/'product') engineer to join our small engineering team - initially to focus on building out a novel interactive tree-based UI. There are some interesting challenges here (and throughout the stack). We're using Python, GraphQL, React/TypeScript, Postgres and AWS, but open minded to adopting technologies that make sense.
We're building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens.
Our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and appropriate responses to more dangerous or more antibiotic resistant strains. We have developed a unique solution to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
I'm looking for an experienced frontend (or full-stack/'product') engineer to join our small engineering team - initially to focus on building out a novel interactive tree-based UI. There are some interesting challenges here (and throughout the stack). We're using Python, GraphQL, React/TypeScript, Postgres and AWS, but open minded to adopting technologies that make sense.
We're building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens.
Our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and appropriate responses to more dangerous or more antibiotic resistant strains. We have developed a unique solution to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
I'm looking for an experienced frontend (or full-stack/'product') engineer to join our small engineering team - initially to focus on building out a novel interactive tree-based UI. There are some interesting challenges here (and throughout the stack). We're using Python, GraphQL, React/TypeScript, Postgres and AWS, but open minded to adopting technologies that make sense.
We're building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens.
Our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and appropriate responses to more dangerous or more antibiotic resistant strains. We have developed a unique solution to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
I'm looking for an experienced frontend (or full-stack/'product') engineer to join our small engineering team - initially to focus on building out a novel interactive tree-based UI. There are some interesting challenges here (and throughout the stack). We're using Python, GraphQL, React/TypeScript, Postgres and AWS, but open minded to adopting technologies that make sense.
Genpax is building a game-changing bacterial analysis platform. Using bioinformatics, we can help hospitals take early and effective action against outbreaks of MRSA and other pathogens. This is an opportunity to have a real-world impact on thousands of lives each year.
At Genpax our goal is to radically increase the utility, scalability, and speed with which whole genome sequencing (WGS) data delivers infection control solutions for human and animal healthcare worldwide. This will enable proactive control at early stages of outbreaks, and to respond appropriately to more dangerous or more antibiotic resistant strains. We have developed unique solutions to address the challenges and our goal is to provide access to these solutions in a fully scalable system.
There are really interesting engineering problems to be solved: scaling and optimising our analysis pipeline and the bioinformatics algorithms we use; building out our interactive graph-based user-facing product; developing cryptographic techniques for analysis of anonymised data. At the moment we're using Python, GraphQL, React/TypeScript, Postgres and AWS.
Beyond standard features (retries, caching, timeouts - enabled with attributes on the decorator), Coflux supports more novel features - like suspense (where a task can choose to go to sleep and get restarted when a result it depends on becomes available), memoisation (where steps within a run are aggressively cached so that you can re-run steps in a workflow without re-running upstream steps), and the ability to re-run a step in a different workspaces (with updated code, or in a different environment).
It turns out this works great for implementing agentic systems - you can provide references to tasks as tools to an LLM call and have the AI drive - tasks can be easily sandboxed. And Claude is very capable of using the CLI to interact with the orchestration server to submit workflows, investigate failed runs, make updates to workflows and re-run steps.
I'm trying to make sure it's easy to try out - there's a self-contained CLI that can be used to start the server (a single Docker container), run worker processes, and then interact with the server. The dev mode automatically restarts the workers as you make local changes. There's also a hosted UI for observing runs in real-time, where you can see the execution graph, access logs/metrics/assets/etc - it works without creating an account - the browser interacts with your orchestration server directly.
reply