01 / Signals AI

One wrong number
can cost
an experiment.
AI 错一个数,
赔进去的
是一轮实验。

Signals AI 帮科学家查实验、筛候选、对数据,我负责它的对话和结果体验。这个案例从一次真实筛选讲起。AI 筛对了 43 个分子,却在一句总结里少算了一个。后面的设计,都从这一个数开始。Signals AI helps scientists search experiments, filter candidates and compare data. I designed its conversations and results. This case starts with a real screening task where the AI got 43 molecules right, then miscounted by one in a single sentence. The design work grew out of that one number.

看看这个项目Explore the case ↓
ROLE我的角色Senior Product Designer高级产品设计师
FOCUS负责范围Conversation, results & evidence对话、结果与证据
COMPANY所属公司Revvity Signals
Signals AI

43 个候选找到了
科学家能放心往下走吗?
43 candidates found
Can the scientist move forward?

Signals AI 能从实验里整理出一份名单。接下来,科学家还要决定查什么、验证什么。我负责从拿到答案到继续研究的这段体验。Signals AI can assemble a shortlist from an experiment. Scientists still need to decide what to inspect and test. My work focuses on the experience between receiving an answer and continuing the research.

先看这份名单是怎么来的See how the shortlist came together
为谁设计THE PEOPLE BEHIND THE RESEARCH

实验台前,
屏幕背后
At the bench
Behind the screen

我的用户是科学家。I DESIGN FOR SCIENTISTS.

他们在实验室做研究,也在电脑前查记录、读结果。我为药企的科学家和研发人员设计,让 Signals AI 接上他们正在做的工作。They run experiments at the bench, then return to a screen to inspect records and results. I design for pharmaceutical scientists and R&D teams, bringing Signals AI into the work already in progress.

科研工作场景插画,一位科学家在实验台操作,两位研究人员在屏幕前讨论
01在实验台前,验证一个想法。At the bench, test an idea.02回到屏幕前,判断下一步。At the screen, decide what comes next.
Signals 的客户SIGNALS CUSTOMERS

他们来自这些药企The companies behind the researchers

Pfizer
辉瑞Pfizer
Merck
默沙东Merck
GSK
葛兰素史克GSK
Roche
罗氏Roche
Novartis
诺华Novartis
AstraZeneca
阿斯利康AstraZeneca
Bayer
拜耳Bayer
Moderna
莫德纳Moderna
我怎样和团队合作HOW I WORK WITH THE TEAM

我的设计,
和三地团队一起完成
My design work
Built with a team across three locations

01

美国 · 产品经理UNITED STATES · PRODUCT MANAGER

Larry

客户调研与部分数据,从他这里进入设计讨论。Customer research and data inform the design discussion through Larry.

02

高级产品设计师SENIOR PRODUCT DESIGNER

Joey Zhao

我负责 AI 入口、筛选,以及对话和结果体验。I design AI entry points, filtering, conversations and results.

03

上海 · 美国SHANGHAI · UNITED STATES

研发工程师Engineering

与研发团队一起完成产品实现。Working with engineering to bring the product to life.

04

印度 · 质量测试INDIA · QUALITY ASSURANCE

QA

由印度团队负责质量测试。Quality assurance with our team in India.

01 / 行业观察 · 2026.1001 / INDUSTRY REVIEW · OCT 2026

同样叫 AI 药物研发,要解决的问题差得很远AI for drug discovery
Very different design problems

Insilico 和 Recursion 把 AI 用在候选药物与实验研究上。Benchling、Signals 则把 AI 放进科学家每天使用的软件。我的问题更具体,实验已经在这里,怎样让 AI 帮人接着做下去?Insilico and Recursion apply AI to drug candidates and experimental research. Benchling and Signals bring AI into scientists’ everyday software. My question is more specific. The experiment is already here. How can AI help someone continue the work?

01研发候选药物Develop drug candidates

02帮助团队完成研究Help teams do research

Revvity Signals我参与的产品THE PRODUCT I WORKED ON

把回答接回正在做的实验Connect the answer to the experiment

AI Explorer 可以围绕实验查找、筛选、分析。Signals One 同时承载实验记录、化学绘图与数据分析。AI Explorer supports search, filtering and analysis around experiments. Signals One also brings together records, chemical drawing and data analysis.

已有工作平台上的 AIAI within an existing research platform

产品官网已展示 AI Explorer;本案例进一步用真实数据检查“提问、筛选、回到记录”这段流程。The product site demonstrates AI Explorer. This case checks the question, filter and return-to-record flow with real data.

看官方产品View the product
对设计的启发DESIGN IMPLICATION

我的重点是入口、筛选依据和回查路径,让平台已有的能力能在一次任务里用起来。My focus is the entry point, filtering criteria and route back to evidence, making the platform’s capabilities usable in one task.

SIGNALS 的产品基础WHAT SIGNALS CAN BUILD ON

实验和工具已经在这里
AI 怎样接进去?
The work is already here
How should AI fit in?

对已经在 Signals 里工作的团队,AI 可以沿用已有实验,并连接 ChemDraw 绘图和 Spotfire 分析。我的设计重点,是让提问、看结果和回查记录连得上。For teams already working in Signals, AI can draw on existing experiments alongside ChemDraw and Spotfire. My design focus is connecting the question, the result and the route back to the record.

Signals One 产品介绍Signals One overview
Signals Notebook实验记录Records团队已有的研究Existing research
ChemDraw化学绘图Chemical drawingChemDraw
Spotfire数据分析Data analysisSpotfire
Signals AI围绕同一份实验继续问Keep asking about the same experiment
我的设计重点MY DESIGN FOCUS看清条件 → 检查答案 → 回到记录Read criteria → Check the answer → Open the record

这也是我想用设计解决的事。
把一句问题,接成一段研究者能继续完成的工作。
This is the design problem I want to solve.
Turn a question into work a scientist can carry forward.

用一个真实任务来看See it through a real task
参考来源Sources +

2026 年 10 月补充调研,依据公开资料比较各产品的主要任务,不作为性能评测。Supplementary research from October 2026, comparing the main tasks of each product using public sources. This is not a performance benchmark.

Signals AI 官方框架Official Signals AI framework
一次真实任务 · 2026 产品复核A REAL TASK · 2026 PRODUCT REVIEW

先给 Signals AI
一个具体问题
Give Signals AI
a concrete question

94 个分子,哪些满足筛选条件?这次用公开实验走一遍,从提问开始,一直查到原始数据。Which of these 94 molecules meet the criteria? This public-data review follows the task from the first question all the way back to the source.

分子Molecule

这次被测试的化合物,还不能叫药。A compound being tested. It is not yet a medicine.

靶点Target

希望影响的对象。这次是名为 CDK2 的蛋白质。The object of the experiment. Here, a protein called CDK2.

IC50

抑制一半活性所需的浓度。同一实验条件下,数值越小,所需浓度越低。The concentration needed for half-maximal inhibition. Under the same assay conditions, a lower value means less is needed.

Signals AI 的筛选结果THE SIGNALS AI FILTERING RESULT

找出 IC50 小于 10 nM 的分子Find molecules with IC50 below 10 nM

nM(纳摩尔每升)是浓度单位。带“>”的记录只说“大于某个数”,没有准确值,先排除。The unit is nM (nanomoles per litre), a concentration. Values marked “>” give only a lower bound, so we exclude them.

94条实验记录experiment records
94原始记录Source records同一公开实验One public assay
88有精确数值Exact values排除只有下限的记录Exclude lower bounds
43小于 10 nMBelow 10 nM排除不满足阈值的记录Exclude values ≥ 10 nM
Signals AI读取附件Read attachmentIC50=< 10 nM列出编号与数值List IDs and values
满足条件Matches未满足条件Does not match仅有下限Lower bound only

每个点对应一条真实记录。Each dot represents one real record.

ChEMBL 公开实验 · 94 条记录ChEMBL public assay · 94 records
43

编号和数值,逐条对上了Every ID and value checked out

Signals AI 完成了这次筛选。对照原始文件,43 条全部一致。Signals AI completed this selection. All 43 matched the original file.

继续核对,发现两类错误TWO ERRORS FOUND ON REVIEW

图表是对的
文字却少算了一个
The chart was right
The summary was one short

问到“小于 100 nM 的有多少个”时,图里三个区间是 1、42、35,文字却写了 77。图对,字错,这种错最难抓,因为整段回答看上去非常可信。我指出矛盾,要它回到原始文件重查,AI 才改成 78,承认自己数错了。Asked how many values were below 100 nM, the chart showed bins of 1, 42 and 35, but the summary said 77. A correct chart with a wrong sentence is the hardest error to catch, because the whole answer looks trustworthy. Only after I pointed out the mismatch and asked for a recheck against the source file did the AI correct it to 78 and admit the miscount.

另一次比较中,AI 把“>1000 nM”解释成了“实验最高只测到 1000 nM”。原文件没有测试范围。我要求它删去这层推断,只保留有记录支持的下限。In a separate comparison, AI treated “>1000 nM” as evidence of the highest concentration tested. The file gave no test range. I asked it to remove that inference and retain only the reported lower bound.

文字总数 · IC50 < 100 nMSUMMARY COUNT · IC50 < 100 nM
7778

图中三个区间:1 + 42 + 35 = 78,与重新查询的结果一致The three chart bins: 1 + 42 + 35 = 78, matching the source recheck

我的设计重点
让数字能核对,推断有出处
My design priority:
Checkable numbers, traceable claims

Signals AI · 把数据画出来SIGNALS AI · SEE THE DISTRIBUTION

把总数与分布
放在一起核对
Check the total
against the distribution

图表里有 88 条精确值。小于 100 nM 的三个区间相加是 78,科学家可以顺着图继续核对。The chart includes 88 exact values. The three bins below 100 nM add up to 78, giving the scientist another way to check the answer.

88条精确值进入图表exact values plotted
Signals AI · 对照候选SIGNALS AI · COMPARE CANDIDATES

三个分子摆在一起
下一轮,先验证谁?
Three molecules
Which should we test next?

这次实验测的是分子抑制 CDK2 的能力,IC50 越低,所需浓度越小。我把数值、比较符号和原始记录放在一起,让科学家看清筛选的依据。This assay measures inhibition of CDK2. A lower IC50 means less compound is needed for the measured effect. I bring values, comparison signs and source records together so scientists can see the basis for selection.

本轮结论:前两个候选优先复测Decision: retest the first two candidates下一步:验证细胞内的效果Next: test activity in cells检查对其他靶点的影响Check effects on other targets

在这三个分子中,0.54 nM 和 1.0 nM 的两个符合 IC50 < 10 nM 的条件,“>1000 nM”的一个不入选。Signals AI 把数据整理成可核对的候选名单,让下一轮实验有明确的起点。Of these three molecules, the two at 0.54 nM and 1.0 nM meet the IC50 < 10 nM criterion; the one reported as >1000 nM does not. Signals AI turns the data into a checkable shortlist—a clear starting point for the next round of experiments.

Signals AI

选择有依据
结果可回查
A reason to select
A source to check

我参与的一次方向讨论A DIRECTION I ARGUED FOR

再做一个 AI 工具,
科学家就要重新开始吗?
A new AI tool
Should scientists have to start over?

最初,团队讨论过另起炉灶,做一个全新的 AI Agent 工具。我一直惦记着另一件事。客户的研究数据已经存在 Signals One 里,这是我们手上最值钱的东西。Early on, the team discussed building an entirely new AI agent tool. I kept coming back to what customers already had: research data accumulated in Signals One. To me, that was our strongest foundation.

我的建议是,让 Signals AI 围绕已有数据工作。科学家不用换个产品从头开始,设计也从“接上正在做的研究”出发。I argued for Signals AI to work with that existing data. Scientists should be able to continue their research without starting again in a new product. That was the direction I wanted the experience to take.

01 / Signals AI

让提问留在实验旁边Keep the question beside the experiment

科学家已经打开了实验,不该再解释一遍“我在看什么”。我把对话留在记录旁边,让 AI 直接接上当前实验、应用和可用数据。The experiment is already open. Scientists should not have to explain it again. I keep the conversation beside the record; the AI also needs the current experiment, application and available data.

少一点工作区宽度,保留眼前的实验。Trade some workspace width for the experiment in view.
02 / Signals AI

先看懂条件,再相信结果Show the rule behind the result

“并且”被理解成“或者”,名单就会变。在这次复核里,我把单位、阈值和比较关系一起留在回答中,让科学家能检查 AI 到底按什么筛选。Read “and” as “or” and the shortlist changes. In this review, I keep the unit, threshold and comparison rule in the answer so scientists can check what the AI actually filtered.

多留一行条件,少一次猜测。One extra line makes the interpretation inspectable.
02.1

这行条件,
值得放大
This line
deserves a closer look

精确值 · nM · 小于 10
43 条匹配,6 条下限记录被排除。
Exact values · nM · Below 10
43 matches; 6 lower-bound records excluded.

03 / Signals AI

答案要有一条回去的路An answer needs a way back

科学家最终要检查的是数据。引用直接接回实验,详细记录留在原处,对话不用越写越长。Scientists ultimately need to inspect the data. A citation returns to the experiment, keeping the conversation brief and the detailed record intact.

摘要留在对话,细节回到记录。A short answer with access to the full record.
03.1

引用,应该能打开A citation should open

从回答里的实验名称,回到 Signals 原始记录。Follow the experiment name in the answer back to its Signals record.

回到实验,决定下一步THE TASK CONTINUES IN THE RECORD

拿到名单以后,
带着依据继续研究
Take the shortlist
Continue with the evidence

从 94 条记录到 43 个候选,每一个都能点回原始数值和来源。名单交到科学家手上时,他们可以先核对,再安排复测,再去验证细胞内的效果和靶点选择性。AI 负责把活干快,信任要靠这几步查回去的路慢慢攒起来。From 94 records to 43 candidates, each one links back to its original value and source. When the shortlist reaches a scientist, they can check it first, then plan retests, cellular assays and selectivity work. The AI makes the work faster. Trust is built one checkable step at a time.

01回答里找到来源Find the citation
02回到实验,继续检查Return to the experiment
Sources and review records数据来源与复核记录 +

2026 年公开数据复核,用于说明当前产品行为。来源为 ChEMBL 的 CDK2 实验,非历史用户研究。Public-data review recorded in 2026 to examine current behavior, separate from historical user research. 查看来源View source IC50 术语来源IC50 reference

比较回答推断了来源没有给出的测试浓度范围,复核后纠正。图表附文把小于 100 nM 的数量算成 77,正确值为 78。完整问答保留在工作档案中。The comparison inferred a concentration range absent from the source. The chart summary also counted 77 values below 100 nM instead of 78. Both were corrected; the full conversation is retained.

材料登记要求数量与纯度,公开数据未提供。因此 94 条数据保存于实验与附件,未登记为实体材料批次。Registration required amount and purity absent from the source. The 94 activities remain in the experiment and attachment; no inventory batches were created.

Source attachment actions来源附件操作
Back to the experiment回到实验
Activity records活性记录
Source details来源详情
Original attachment原始附件
Public assay source公开实验来源
实验与原始附件Experiment and source file
筛选条件局部Filtering detail
修正后的比较回答Corrected comparison
活性分布Activity distribution
公开化合物结构Public compound structures
Signals AI · 产品后续进展SIGNALS AI · PRODUCT MILESTONE

后来,Signals AI
也走进了 Claude
Signals AI now reaches
scientists in Claude, too

Revvity 宣布接入 Anthropic 的 MCP 连接器生态。科学家可以在 Claude 里访问 Signals 中的实验和研究信息,继续查询与分析。Revvity announced its integration with Anthropic’s MCP connector ecosystem. Scientists can access experiments and research context from Signals while working in Claude.

MCP 可以理解为连接 AI 与科研系统的接口。换一个地方提问,照样能访问 Signals 里的研究信息。MCP connects an AI assistant to a scientific system: a different place to ask, with access to the research in Signals.
CONTINUE EXPLORING继续探索Material traceability
for scientists
为科学家设计
材料追溯图