Pinned Tweet
What does it mean to be on #TeamScience? Find out what Benchlings have to say about our mission and culture — and above all, why we’re so passionate about helping scientists power new possibilities for humanity. youtu.be/KiBmXAGoMgU
8
9
39
Benchling retweeted
Day 16 of “An agent a day keeps Phase 2 failures away” — wiki builder
Tacit knowledge accumulates in every company, but it’s especially pernicious in biotechs. Which cell line should you use for this experiment? Does this machine have a technical artifact? This knowledge can be nto a persistent, shareable record. But staying on top of all the science that’s going on and converting it into digestible facts is too much for a person to do. Enter the Wiki creation agent.
Sample prompt (feel free to tweak): Create a Wiki agent that runs every evening. It should look at all the work that had been done during the day and record any meaningful result in a wiki file. If there was no meaningful progress to be recorded, say so. The wiki should be in the Open Knowledge Format and placed in the appropriate project/folder. Make sure every piece of information has a link back to the source information (ELN entry, registered entity, result, etc). Give me a summary of what was updated.
Tacit knowledge accumulates in every company, but it’s especially pernicious in biotechs. Which cell line should you use for this experiment? Does this machine have a technical artifact? This knowledge can be nto a persistent, shareable record. But staying on top of all the science that’s going on and converting it into digestible facts is too much for a person to do. Enter the Wiki creation agent.
Sample prompt (feel free to tweak): Create a Wiki agent that runs every evening. It should look at all the work that had been done during the day and record any meaningful result in a wiki file. If there was no meaningful progress to be recorded, say so. The wiki should be in the Open Knowledge Format and placed in the appropriate project/folder. Make sure every piece of information has a link back to the source information (ELN entry, registered entity, result, etc). Give me a summary of what was updated.
0
1
3
311
Benchling retweeted
SLIDES! GANTT CHARTS! Every scientist’s (least) favorite topic
Keeping track of all the ongoing work in a program is extremely difficult. Especially if you’re asking everyone to take time out of their day to update a tracker. But if you want to scale to more programs without ou’ll need some way of managing bottlenecks and staying on top of what’s happening. That’s where an agent can come in handy.
Sample prompt (feel free to tweak): Create a Program Management Agent which gives me a status update on all of our ongoing programs and calls out any delays or blockers. Include a Gantt chart of our progress. Format the update as a slide deck.
Day 15 of “An agent a day keeps Phase 2 failures away” — program manager
Keeping track of all the ongoing work in a program is extremely difficult. Especially if you’re asking everyone to take time out of their day to update a tracker. But if you want to scale to more programs without ou’ll need some way of managing bottlenecks and staying on top of what’s happening. That’s where an agent can come in handy.
Sample prompt (feel free to tweak): Create a Program Management Agent which gives me a status update on all of our ongoing programs and calls out any delays or blockers. Include a Gantt chart of our progress. Format the update as a slide deck.
Day 15 of “An agent a day keeps Phase 2 failures away” — program manager
1
3
4
632
Benchling retweeted
Lots of discussion recently about target crowding. Some of that is intentional (derisked biology), but some of it comes out of ignorance of how many companies are going after the same indication. Staying up to date on the market has never been easier. Set up a competitive ake sure you’re informed about what’s happening to your pipeline.
Sample prompt (feel free to tweak): Create a Competitive Intelligence Agent that runs every Sunday and gives me a full report on the last week. Focus on our lead programs. The first time you run, compile a list of relevant companies and labs and save it to your memory. Then, every report should give me an update on any progress or announcements (press releases, LinkedIn posts, conference presentations, etc). Make sure to also keep an eye out for any new entrants who weren’t on the original list.
Day 14 of “An agent a day keeps Phase 2 failures away” — competitive intelligence
Sample prompt (feel free to tweak): Create a Competitive Intelligence Agent that runs every Sunday and gives me a full report on the last week. Focus on our lead programs. The first time you run, compile a list of relevant companies and labs and save it to your memory. Then, every report should give me an update on any progress or announcements (press releases, LinkedIn posts, conference presentations, etc). Make sure to also keep an eye out for any new entrants who weren’t on the original list.
Day 14 of “An agent a day keeps Phase 2 failures away” — competitive intelligence
0
2
8
647
Benchling retweeted
Many people assuming that just because I posted this means I think LLMs will not get better at biology... not sure why, I agree this is a task with a nice verifiable reward that LLMs will certainly get better at.
However it shows how much tacit knowledge is in biology and how spiky the intelligence of these models is. Many tasks that are much harder to verify (e.g. program decisions, target ID)
However it shows how much tacit knowledge is in biology and how spiky the intelligence of these models is. Many tasks that are much harder to verify (e.g. program decisions, target ID)
I hate to rain on everyone's parade, but unfortunately LLMs are still not that good at biology :(. Even basic molecular cloning tasks are beyond the reach of frontier models
1
4
16
1,814
Benchling retweeted
Yesterday we showed how to automatically import and structure CRO data. But what happens when those pipelines fail? Whether it’s getting data in a slightly different format, a firmware update to an instrument, or a new plate format — new data is constantly breaking deterministic gent can help you get the best of both worlds: use pipelines when you can, but automatically recover from errors as the science and data evolve.
Sample prompt (feel free to tweak): Create a Pipeline Agent that automatically monitors analysis pipelines that fail. When a pipeline fails, it should diagnose what happened (e.g. wrong file, data shape changed, transient issue, etc) and then perform the appropriate fix. If the fix involves changing the pipeline code, it should create a new draft of the pipeline but not publish it.
Day 13 of “An agent a day keeps Phase 2 failures away” — automatically unblock pipelines
Sample prompt (feel free to tweak): Create a Pipeline Agent that automatically monitors analysis pipelines that fail. When a pipeline fails, it should diagnose what happened (e.g. wrong file, data shape changed, transient issue, etc) and then perform the appropriate fix. If the fix involves changing the pipeline code, it should create a new draft of the pipeline but not publish it.
Day 13 of “An agent a day keeps Phase 2 failures away” — automatically unblock pipelines
Day 12 of “An agent a day keeps Phase 2 failures away” — automate CRO data ingestion
Everyone is buzzing about one person biotechs who are heavily leveraging CROs. But basically every biotech and pharma company uses CROs. And scientists waste hours each week monitoring their data. What if the data just showed up how you needed it, when you needed it, in the place you’re already doing your daily work?
Sample prompt (feel free to tweak): Create a CRO Agent which takes any new files in our CRO project and automatically runs the correct pipeline to parse and structure the data. Then, take the outputs of the pipeline and create a notebook entry that includes all the structured data we extracted as well as a summary slide deck.
s/o Clare Young for the guest video
0
3
12
796
Benchling retweeted
Day 12 of “An agent a day keeps Phase 2 failures away” — automate CRO data ingestion
Everyone is buzzing about one person biotechs who are heavily leveraging CROs. But basically every biotech and pharma company uses CROs. And scientists waste hours each week monitoring their data. What if the data just showed up how you needed it, when you needed it, in the place you’re already doing your daily work?
Sample prompt (feel free to tweak): Create a CRO Agent which takes any new files in our CRO project and automatically runs the correct pipeline to parse and structure the data. Then, take the outputs of the pipeline and create a notebook entry that includes all the structured data we extracted as well as a summary slide deck.
s/o Clare Young for the guest video
Everyone is buzzing about one person biotechs who are heavily leveraging CROs. But basically every biotech and pharma company uses CROs. And scientists waste hours each week monitoring their data. What if the data just showed up how you needed it, when you needed it, in the place you’re already doing your daily work?
Sample prompt (feel free to tweak): Create a CRO Agent which takes any new files in our CRO project and automatically runs the correct pipeline to parse and structure the data. Then, take the outputs of the pipeline and create a notebook entry that includes all the structured data we extracted as well as a summary slide deck.
s/o Clare Young for the guest video
1
1
9
1,652
Benchling retweeted
We worked with scientific experts to build cloning tasks from real experiments and then tested leading models. GPT-6 Astra led at 30.6%, followed by GPT-6.1 Sol at 22.2% and Claude Opus 5.5 at 20.5%. Less recent models scored just 8-10%.
1
1
2
230
Benchling retweeted
How good is AI at molecular biology? Our newest benchmark, BenchBench-Cloning, shows recent models have gotten a lot better, but still have a ways to go.
1
1
14
1,556
Benchling retweeted
How good is AI at molecular biology?
Cloning is foundational to molecular biology. I did plenty of it during my wet lab stints. We decided to set AI to the task. Introducing BenchBench-Cloning.
GPT-6 Astra led with a score of 30.6%, followed by GPT-6.1 Sol at 22.2% and Claude se tasks require long, multi-step reasoning. Models frequently make the right individual decisions but struggle to put them together.
Read more: benchling.com/blog/how-good-…
Cloning is foundational to molecular biology. I did plenty of it during my wet lab stints. We decided to set AI to the task. Introducing BenchBench-Cloning.
GPT-6 Astra led with a score of 30.6%, followed by GPT-6.1 Sol at 22.2% and Claude se tasks require long, multi-step reasoning. Models frequently make the right individual decisions but struggle to put them together.
Read more: benchling.com/blog/how-good-…
1
1
14
787
Benchling retweeted
I hate to rain on everyone's parade, but unfortunately LLMs are still not that good at biology :(. Even basic molecular cloning tasks are beyond the reach of frontier models
42
25
271
28,148
AI can analyze DNA sequences. But can it design an entire molecular cloning experiment?
Introducing BenchBench-Cloning, our new benchmark that evaluates leading AI models on 65 real-world molecular cloning tasks.
Get the results and preprint: benchling.com/blog/how-good-…
Introducing BenchBench-Cloning, our new benchmark that evaluates leading AI models on 65 real-world molecular cloning tasks.
Get the results and preprint: benchling.com/blog/how-good-…
1
7
47
3,122
Benchling retweeted
I call this one the “did you” agent.
Day 11 of “An agent a day keeps Phase 2 failures away” — data QC
Doing rigorous QC of your data requires answering a lot of questions. Did you check for transcription errors? Did you check if two samples got swapped? Did you check for for edge effects? Did you check for contamination? Did you check if a control is drifting? Did you check for batch effects? Did you check if different operators have different distributions of results? Let’s make an agent to help us automatically answer this question.
Sample prompt (feel free to tweak): Create a QC Agent which runs every day and looks at all of the new data for our program. It should do rigorous QC over the data and look for the following: transcription errors, sample swapping, outliers, edge effects, contamination, control drift, batch effects, operator effects, and any other potential data issues. Give me a full report on any issues and suggest next steps to remediate them or say that there are no issues.
Day 11 of “An agent a day keeps Phase 2 failures away” — data QC
Doing rigorous QC of your data requires answering a lot of questions. Did you check for transcription errors? Did you check if two samples got swapped? Did you check for for edge effects? Did you check for contamination? Did you check if a control is drifting? Did you check for batch effects? Did you check if different operators have different distributions of results? Let’s make an agent to help us automatically answer this question.
Sample prompt (feel free to tweak): Create a QC Agent which runs every day and looks at all of the new data for our program. It should do rigorous QC over the data and look for the following: transcription errors, sample swapping, outliers, edge effects, contamination, control drift, batch effects, operator effects, and any other potential data issues. Give me a full report on any issues and suggest next steps to remediate them or say that there are no issues.
0
2
5
583
Benchling retweeted
Day 10 of “An agent a day keeps Phase 2 failures away” — inventory
There’s no worse feeling than starting an experiment and realizing that you’ve run out of a key reagent. Or that something is past its expiration date. But keeping track of every reagent or component of an work. So most of us don’t bother to keep our digital inventory up to date. What if we had an agent that could keep it up to date without doing any additional work (other than keeping a good notebook entry)?
Sample prompt (feel free to tweak): Create an Inventory Agent which runs every day at all of the experiments which were run and updates our inventory (plates, reagents, stocks, etc) based on what was actually used. Also mention if anything is out of date or expired. If anything in our inventory seems to be running low, queue up an order for my approval.
There’s no worse feeling than starting an experiment and realizing that you’ve run out of a key reagent. Or that something is past its expiration date. But keeping track of every reagent or component of an work. So most of us don’t bother to keep our digital inventory up to date. What if we had an agent that could keep it up to date without doing any additional work (other than keeping a good notebook entry)?
Sample prompt (feel free to tweak): Create an Inventory Agent which runs every day at all of the experiments which were run and updates our inventory (plates, reagents, stocks, etc) based on what was actually used. Also mention if anything is out of date or expired. If anything in our inventory seems to be running low, queue up an order for my approval.
0
1
4
496
Benchling retweeted
I tell everyone that @divergence_labs is one of the most impressive early stage biotech teams. Excited to see them start telling their story.
Today, in collaboration with Anthropic, we’re excited to share rapid initial progress towards an antibody treatment for food allergy, which affects over 200 million people worldwide, discovered with the help of Claude.
At Divergence Labs, we believe that AI can unlock the next therapeutics with more effective mechanisms than before. Such mechanisms are urgently needed in food allergy, which involve overcoming one of the tightest affinity protein pairs in immunology, IgE and its receptor FcεRI, on mast cells.
Treatment with Xolair—the only approved antibody for food allergy—sequesters circulating IgE, but mast cells remain sensitized for weeks to months due to the extraordinarily slow dissociation of IgE from FcεRI.
We envision a treatment that actively pulls IgE off of FcεRI, without waiting for natural dissociation. Like picking a lock, this requires the right combination of geometry and force.
Our research team, working with Claude, ideated on mechanisms to accomplish this disruption, and converged on an antibody format with two arms with different functions and epitopes. Within one month, we designed, synthesized, and experimentally confirmed the biophysical function of the two arms, which we are now assembling into full therapeutic formats.
1
3
64
7,296
Benchling retweeted
Day 9 of “An agent a day keeps Phase 2 failures away” — patents
IP is the lifeblood of biotech, but most data is hidden away and never examined after the initial experiment. However, I’ve been seeing more legal teams use our AI tools to look for novel research that can be anies don’t have dedicated patent attorneys or a large enough legal team to handle all of the research that is being produced. Luckily, you can just set up an agent to do that search on your behalf.
Sample prompt (feel free to tweak): Create a monthly Patentable Discoveries Agent which runs every month and looks at all of the research that has been done and identifies up to 3 pieces of work that could be patented. If there are no discoveries that rise to the level of a patentable piece of work, it says so and suggests how existing work would need to be extended to be a novel, patentable discovery.
IP is the lifeblood of biotech, but most data is hidden away and never examined after the initial experiment. However, I’ve been seeing more legal teams use our AI tools to look for novel research that can be anies don’t have dedicated patent attorneys or a large enough legal team to handle all of the research that is being produced. Luckily, you can just set up an agent to do that search on your behalf.
Sample prompt (feel free to tweak): Create a monthly Patentable Discoveries Agent which runs every month and looks at all of the research that has been done and identifies up to 3 pieces of work that could be patented. If there are no discoveries that rise to the level of a patentable piece of work, it says so and suggests how existing work would need to be extended to be a novel, patentable discovery.
0
1
9
546
Benchling retweeted
Day 8 of “An agent a day keeps Phase 2 failures away” — higher quality notebook entries
Notebook entries are the foundation of a biotech’s scientific record. If they’re not accurate, high quality, and up to date, anything you try to do downstream will be more challenging. Most ecording their work as a tax, not something they look forward to. But what if there was an agent that could help keep the quality of notebook entries high without requiring more work from already busy scientists…
Sample prompt (feel free to tweak): Create a Notebook Review Agent which runs when a notebook entry is sent for review. The agent should look over the entry and check for any data issues (e.g. transcription errors), the quality and clarity of the prose, as well as the overall completeness of the entry. If there are attached data files that haven’t been put into a structured form, extract the data and put it into structured tables. After reviewing the full entry, the agent should make a few recommendations of what the author should do based on the entry.
Notebook entries are the foundation of a biotech’s scientific record. If they’re not accurate, high quality, and up to date, anything you try to do downstream will be more challenging. Most ecording their work as a tax, not something they look forward to. But what if there was an agent that could help keep the quality of notebook entries high without requiring more work from already busy scientists…
Sample prompt (feel free to tweak): Create a Notebook Review Agent which runs when a notebook entry is sent for review. The agent should look over the entry and check for any data issues (e.g. transcription errors), the quality and clarity of the prose, as well as the overall completeness of the entry. If there are attached data files that haven’t been put into a structured form, extract the data and put it into structured tables. After reviewing the full entry, the agent should make a few recommendations of what the author should do based on the entry.
0
1
6
647
Benchling retweeted
This one is for all my LabOps folks!
Day 7 of “An agent a day keeps Phase 2 failures away” — equipment
Most lab equipment costs hundreds of thousands (or sometimes millions) of dollars. So why wouldn’t you have an agent making sure there’s contamination or miscalibration on any aining a lot of equipment is challenging, but knowing when something needs your attention is half the battle: and an agent can help with that.
Sample prompt (feel free to tweak): Create an Equipment Monitor that runs every week and looks at all experiments run on a piece of equipment to determine if the machine might be miscalibrated, needs to be maintained, or is contaminated. Make sure it reports it as a full canvas depiction of the current state of our equipment.
Day 7 of “An agent a day keeps Phase 2 failures away” — equipment
Most lab equipment costs hundreds of thousands (or sometimes millions) of dollars. So why wouldn’t you have an agent making sure there’s contamination or miscalibration on any aining a lot of equipment is challenging, but knowing when something needs your attention is half the battle: and an agent can help with that.
Sample prompt (feel free to tweak): Create an Equipment Monitor that runs every week and looks at all experiments run on a piece of equipment to determine if the machine might be miscalibrated, needs to be maintained, or is contaminated. Make sure it reports it as a full canvas depiction of the current state of our equipment.
0
4
7
826
Benchling retweeted
Better science doesn't stop on the weekends! Day 6 of “An agent a day keeps Phase 2 failures away” — save $10M
A biotech company once told me that they used Benchling AI to determine that 30% of their in vivo studies were redundant or wasteful. That’s millions of dollars and drain. Every animal study should have an agent (or really a team of agents) making sure it is designed correctly and will provide useful results.
Sample prompt (feel free to tweak): Create an In Vivo Study Review agent that runs before an study moves to its execution stage. Analyze whether it’s a duplicate of an existing study and if it the readout will be statistically significant. If there are changes that should be made, provide concrete suggestions on how to update the study design.
A biotech company once told me that they used Benchling AI to determine that 30% of their in vivo studies were redundant or wasteful. That’s millions of dollars and drain. Every animal study should have an agent (or really a team of agents) making sure it is designed correctly and will provide useful results.
Sample prompt (feel free to tweak): Create an In Vivo Study Review agent that runs before an study moves to its execution stage. Analyze whether it’s a duplicate of an existing study and if it the readout will be statistically significant. If there are changes that should be made, provide concrete suggestions on how to update the study design.
3
3
21
4,463
Benchling retweeted
Day 5 of “An agent a day keeps Phase 2 failures away” — literature review
Literature Review is probably the most common way I see scientists use AI. AI tools have come a long way since the early days of ChatGPT when they used to hallucinate references, but most scientists are ts full potential. If you set up a lit review agent that is *based on your actual experimental data* you will get much better results.
Sample prompt (feel free to tweak): Create a weekly Literature Review agent that runs every Friday morning and surveys the latest literature relevant to my work. In particular, look for papers that include new techniques that could accelerate my science or papers that contain data that might confirm or refute my current research direction.
Literature Review is probably the most common way I see scientists use AI. AI tools have come a long way since the early days of ChatGPT when they used to hallucinate references, but most scientists are ts full potential. If you set up a lit review agent that is *based on your actual experimental data* you will get much better results.
Sample prompt (feel free to tweak): Create a weekly Literature Review agent that runs every Friday morning and surveys the latest literature relevant to my work. In particular, look for papers that include new techniques that could accelerate my science or papers that contain data that might confirm or refute my current research direction.
1
1
10
671
Benchling retweeted
Thank you to Ed Pilkington and John Levy for making biology so exciting, and to the many teachers, students and colleagues I've learned from since. Grateful to @stephgreed and @NatRevChem for this birthday Q&A.
rdcu.be/1nwbXTvbRpWa
rdcu.be/1nwbXTvbRpWa
4
17
128
17,568